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

Dataset: The Pile

Neuron 3896 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: 0.4505. Min Range: -0.4505

Max Act: 0.4505. Min Act: -0.0000

Data Index: 1124668 (The Pile)

Max Activating Token Index: 619

Text #1

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3753. Min Act: -0.0000

Data Index: 1449930 (The Pile)

Max Activating Token Index: 395

Text #2

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.4189. Min Act: -0.0000

Data Index: 219675 (The Pile)

Max Activating Token Index: 88

Text #3

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3479. Min Act: -0.0000

Data Index: 1774510 (The Pile)

Max Activating Token Index: 854

Text #4

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3712. Min Act: -0.0000

Data Index: 1592927 (The Pile)

Max Activating Token Index: 897

Text #5

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3629. Min Act: -0.0000

Data Index: 479614 (The Pile)

Max Activating Token Index: 663

Text #6

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3391. Min Act: -0.0000

Data Index: 881690 (The Pile)

Max Activating Token Index: 422

Text #7

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3739. Min Act: -0.0000

Data Index: 701997 (The Pile)

Max Activating Token Index: 430

Text #8

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3492. Min Act: -0.0000

Data Index: 1225888 (The Pile)

Max Activating Token Index: 969

Text #9

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3440. Min Act: -0.0000

Data Index: 1345483 (The Pile)

Max Activating Token Index: 997

Text #10

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3397. Min Act: -0.0000

Data Index: 1754584 (The Pile)

Max Activating Token Index: 377

Text #11

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3244. Min Act: -0.0000

Data Index: 1960486 (The Pile)

Max Activating Token Index: 281

Text #12

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3208. Min Act: -0.0000

Data Index: 1242320 (The Pile)

Max Activating Token Index: 724

Text #13

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3333. Min Act: -0.0000

Data Index: 1857745 (The Pile)

Max Activating Token Index: 1017

Text #14

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3283. Min Act: -0.0000

Data Index: 294728 (The Pile)

Max Activating Token Index: 100

Text #15

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3382. Min Act: -0.0000

Data Index: 290725 (The Pile)

Max Activating Token Index: 345

Text #16

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3160. Min Act: -0.0000

Data Index: 1759224 (The Pile)

Max Activating Token Index: 924

Text #17

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3369. Min Act: -0.0000

Data Index: 1715419 (The Pile)

Max Activating Token Index: 122

Text #18

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3238. Min Act: -0.0000

Data Index: 241932 (The Pile)

Max Activating Token Index: 875

Text #19

Max Range: 0.4505. Min Range: -0.4505

Max Act: 0.3241. Min Act: -0.0000

Data Index: 1139468 (The Pile)

Max Activating Token Index: 377