< Prev | Home | Model | Random | Next >

Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.3768. Min Act: -0.0001

Data Index: 81452 (The Pile)

Max Activating Token Index: 312

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.3398. Min Act: -0.0001

Data Index: 1387063 (The Pile)

Max Activating Token Index: 589

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.3359. Min Act: -0.0001

Data Index: 1163397 (The Pile)

Max Activating Token Index: 891

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.3727. Min Act: -0.0001

Data Index: 1495434 (The Pile)

Max Activating Token Index: 429

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.3396. Min Act: -0.0001

Data Index: 1120447 (The Pile)

Max Activating Token Index: 583

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.3452. Min Act: -0.0001

Data Index: 370046 (The Pile)

Max Activating Token Index: 659

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.3296. Min Act: -0.0001

Data Index: 323855 (The Pile)

Max Activating Token Index: 469

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2955. Min Act: -0.0001

Data Index: 684101 (The Pile)

Max Activating Token Index: 747

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.3212. Min Act: -0.0001

Data Index: 678547 (The Pile)

Max Activating Token Index: 67

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.3374. Min Act: -0.0001

Data Index: 1963377 (The Pile)

Max Activating Token Index: 637

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.3469. Min Act: -0.0001

Data Index: 1798420 (The Pile)

Max Activating Token Index: 526

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2916. Min Act: -0.0001

Data Index: 655906 (The Pile)

Max Activating Token Index: 187

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.3151. Min Act: -0.0001

Data Index: 1961486 (The Pile)

Max Activating Token Index: 341

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.3046. Min Act: -0.0001

Data Index: 711581 (The Pile)

Max Activating Token Index: 465

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2871. Min Act: -0.0001

Data Index: 537621 (The Pile)

Max Activating Token Index: 609

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2849. Min Act: -0.0001

Data Index: 208255 (The Pile)

Max Activating Token Index: 337

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2963. Min Act: -0.0001

Data Index: 1156470 (The Pile)

Max Activating Token Index: 108

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2891. Min Act: -0.0001

Data Index: 1888729 (The Pile)

Max Activating Token Index: 449

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2748. Min Act: -0.0001

Data Index: 1221805 (The Pile)

Max Activating Token Index: 658

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.3768. Min Range: -0.3768

Max Act: 0.2989. Min Act: -0.0001

Data Index: 1897504 (The Pile)

Max Activating Token Index: 754

Click toggle to see full text

Truncated

Full Text #19