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

Dataset: The Pile

Neuron 3863 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.7269. Min Act: -0.0000

Data Index: 589274 (The Pile)

Max Activating Token Index: 231

Text #1

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.5699. Min Act: -0.0000

Data Index: 446000 (The Pile)

Max Activating Token Index: 888

Text #2

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.5152. Min Act: 0.0000

Data Index: 953462 (The Pile)

Max Activating Token Index: 46

Text #3

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.5293. Min Act: -0.0000

Data Index: 1263455 (The Pile)

Max Activating Token Index: 564

Text #4

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.4507. Min Act: -0.0000

Data Index: 1567354 (The Pile)

Max Activating Token Index: 611

Text #5

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.4724. Min Act: 0.0000

Data Index: 1991582 (The Pile)

Max Activating Token Index: 394

Text #6

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1324486 (The Pile)

Max Activating Token Index: 485

Text #7

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.4535. Min Act: 0.0000

Data Index: 1903834 (The Pile)

Max Activating Token Index: 266

Text #8

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.4192. Min Act: -0.0000

Data Index: 1730612 (The Pile)

Max Activating Token Index: 30

Text #9

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.4440. Min Act: -0.0000

Data Index: 1184909 (The Pile)

Max Activating Token Index: 302

Text #10

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.3972. Min Act: -0.0000

Data Index: 966720 (The Pile)

Max Activating Token Index: 700

Text #11

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.4004. Min Act: -0.0000

Data Index: 1946998 (The Pile)

Max Activating Token Index: 650

Text #12

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.3843. Min Act: -0.0000

Data Index: 265023 (The Pile)

Max Activating Token Index: 788

Text #13

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.3836. Min Act: -0.0000

Data Index: 1283240 (The Pile)

Max Activating Token Index: 441

Text #14

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.3911. Min Act: -0.0000

Data Index: 132051 (The Pile)

Max Activating Token Index: 603

Text #15

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.3749. Min Act: -0.0000

Data Index: 322103 (The Pile)

Max Activating Token Index: 487

Text #16

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.3841. Min Act: -0.0000

Data Index: 294798 (The Pile)

Max Activating Token Index: 928

Text #17

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.3473. Min Act: -0.0000

Data Index: 64737 (The Pile)

Max Activating Token Index: 712

Text #18

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.3852. Min Act: -0.0000

Data Index: 210892 (The Pile)

Max Activating Token Index: 82

Text #19

Max Range: 0.7269. Min Range: -0.7269

Max Act: 0.3510. Min Act: -0.0000

Data Index: 1928714 (The Pile)

Max Activating Token Index: 904