< Prev | Home | Model | Random | Next >

Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2375 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')



Text #0

Max Range: 1.3525. Min Range: -1.3525

Max Act: 1.3525. Min Act: 0.0000

Data Index: 673987 (C4 (Web Text))

Max Activating Token Index: 353

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.3525. Min Range: -1.3525

Max Act: 1.1865. Min Act: -0.0000

Data Index: 157227 (C4 (Web Text))

Max Activating Token Index: 337

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.3525. Min Range: -1.3525

Max Act: 1.1840. Min Act: -0.0000

Data Index: 247721 (C4 (Web Text))

Max Activating Token Index: 550

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.3525. Min Range: -1.3525

Max Act: 1.1543. Min Act: 0.0000

Data Index: 335366 (C4 (Web Text))

Max Activating Token Index: 47

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.3525. Min Range: -1.3525

Max Act: 1.1981. Min Act: -0.0000

Data Index: 938163 (C4 (Web Text))

Max Activating Token Index: 944

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.3525. Min Range: -1.3525

Max Act: 1.1959. Min Act: -0.0000

Data Index: 137976 (C4 (Web Text))

Max Activating Token Index: 759

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.3525. Min Range: -1.3525

Max Act: 1.1338. Min Act: -0.0000

Data Index: 556177 (C4 (Web Text))

Max Activating Token Index: 383

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.3525. Min Range: -1.3525

Max Act: 1.1113. Min Act: 0.0001

Data Index: 292652 (C4 (Web Text))

Max Activating Token Index: 438

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.3525. Min Range: -1.3525

Max Act: 1.1120. Min Act: -0.0000

Data Index: 1395726 (Python Code)

Max Activating Token Index: 260

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.3525. Min Range: -1.3525

Max Act: 1.1065. Min Act: 0.0000

Data Index: 798604 (C4 (Web Text))

Max Activating Token Index: 693

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.3525. Min Range: -1.3525

Max Act: 1.0946. Min Act: 0.0000

Data Index: 693434 (C4 (Web Text))

Max Activating Token Index: 481

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.3525. Min Range: -1.3525

Max Act: 1.0805. Min Act: -0.0000

Data Index: 894490 (C4 (Web Text))

Max Activating Token Index: 801

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.3525. Min Range: -1.3525

Max Act: 1.0858. Min Act: -0.0000

Data Index: 23385 (C4 (Web Text))

Max Activating Token Index: 744

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.3525. Min Range: -1.3525

Max Act: 1.0736. Min Act: 0.0000

Data Index: 821881 (C4 (Web Text))

Max Activating Token Index: 677

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.3525. Min Range: -1.3525

Max Act: 1.0677. Min Act: -0.0000

Data Index: 817913 (C4 (Web Text))

Max Activating Token Index: 487

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.3525. Min Range: -1.3525

Max Act: 1.0532. Min Act: -0.0000

Data Index: 1484775 (Python Code)

Max Activating Token Index: 860

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.3525. Min Range: -1.3525

Max Act: 1.0391. Min Act: 0.0000

Data Index: 739835 (C4 (Web Text))

Max Activating Token Index: 251

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.3525. Min Range: -1.3525

Max Act: 1.0293. Min Act: -0.0000

Data Index: 736259 (C4 (Web Text))

Max Activating Token Index: 370

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.3525. Min Range: -1.3525

Max Act: 1.0829. Min Act: -0.0000

Data Index: 218673 (C4 (Web Text))

Max Activating Token Index: 361

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.3525. Min Range: -1.3525

Max Act: 1.0892. Min Act: -0.0000

Data Index: 1425496 (Python Code)

Max Activating Token Index: 527

Click toggle to see full text

Truncated

Full Text #19