< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 243 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.4325. Min Range: -3.4325

Max Act: 3.3099. Min Act: 0.0001

Data Index: 1875090 (The Pile)

Max Activating Token Index: 975

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.4325. Min Range: -3.4325

Max Act: 3.4325. Min Act: -0.0000

Data Index: 683078 (The Pile)

Max Activating Token Index: 465

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.4325. Min Range: -3.4325

Max Act: 3.1465. Min Act: 0.0001

Data Index: 1365592 (The Pile)

Max Activating Token Index: 457

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.4325. Min Range: -3.4325

Max Act: 3.0922. Min Act: 0.0000

Data Index: 1230949 (The Pile)

Max Activating Token Index: 356

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.4325. Min Range: -3.4325

Max Act: 3.0826. Min Act: 0.0000

Data Index: 1723424 (The Pile)

Max Activating Token Index: 532

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.4325. Min Range: -3.4325

Max Act: 3.2399. Min Act: -0.0000

Data Index: 227733 (The Pile)

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.4325. Min Range: -3.4325

Max Act: 3.0995. Min Act: 0.0001

Data Index: 647481 (The Pile)

Max Activating Token Index: 330

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.4325. Min Range: -3.4325

Max Act: 3.0681. Min Act: -0.0000

Data Index: 649742 (The Pile)

Max Activating Token Index: 516

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.4325. Min Range: -3.4325

Max Act: 3.0282. Min Act: 0.0001

Data Index: 1877459 (The Pile)

Max Activating Token Index: 460

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.4325. Min Range: -3.4325

Max Act: 3.0185. Min Act: -0.0000

Data Index: 268879 (The Pile)

Max Activating Token Index: 993

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.4325. Min Range: -3.4325

Max Act: 2.7973. Min Act: 0.0001

Data Index: 898146 (The Pile)

Max Activating Token Index: 553

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.4325. Min Range: -3.4325

Max Act: 2.9397. Min Act: -0.0000

Data Index: 661920 (The Pile)

Max Activating Token Index: 1003

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.4325. Min Range: -3.4325

Max Act: 2.7630. Min Act: 0.0001

Data Index: 1665297 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.4325. Min Range: -3.4325

Max Act: 2.7664. Min Act: -0.0000

Data Index: 575031 (The Pile)

Max Activating Token Index: 619

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.4325. Min Range: -3.4325

Max Act: 2.9000. Min Act: 0.0001

Data Index: 205003 (The Pile)

Max Activating Token Index: 847

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.4325. Min Range: -3.4325

Max Act: 2.7560. Min Act: 0.0002

Data Index: 1560891 (The Pile)

Max Activating Token Index: 82

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.4325. Min Range: -3.4325

Max Act: 2.8500. Min Act: 0.0000

Data Index: 1563260 (The Pile)

Max Activating Token Index: 516

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.4325. Min Range: -3.4325

Max Act: 2.8348. Min Act: 0.0002

Data Index: 270833 (The Pile)

Max Activating Token Index: 245

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.4325. Min Range: -3.4325

Max Act: 2.7860. Min Act: -0.0000

Data Index: 1799147 (The Pile)

Max Activating Token Index: 798

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.4325. Min Range: -3.4325

Max Act: 2.7895. Min Act: 0.0001

Data Index: 1726551 (The Pile)

Max Activating Token Index: 468

Click toggle to see full text

Truncated

Full Text #19