Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4480 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.7413. Min Act: -0.0000

Data Index: 1589680 (The Pile)

Max Activating Token Index: 743

Text #1

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.6566. Min Act: -0.0000

Data Index: 464912 (The Pile)

Max Activating Token Index: 44

Text #2

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.6907. Min Act: -0.0000

Data Index: 1459716 (The Pile)

Max Activating Token Index: 238

Text #3

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.6511. Min Act: -0.0000

Data Index: 653344 (The Pile)

Max Activating Token Index: 489

Text #4

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.6246. Min Act: -0.0000

Data Index: 735113 (The Pile)

Max Activating Token Index: 313

Text #5

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.6170. Min Act: -0.0000

Data Index: 411851 (The Pile)

Max Activating Token Index: 216

Text #6

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.6156. Min Act: -0.0000

Data Index: 1996350 (The Pile)

Max Activating Token Index: 435

Text #7

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.5990. Min Act: -0.0000

Data Index: 1657670 (The Pile)

Max Activating Token Index: 410

Text #8

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.5882. Min Act: -0.0000

Data Index: 813371 (The Pile)

Max Activating Token Index: 416

Text #9

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.5952. Min Act: -0.0000

Data Index: 137794 (The Pile)

Max Activating Token Index: 848

Text #10

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.5520. Min Act: -0.0000

Data Index: 1075679 (The Pile)

Max Activating Token Index: 1008

Text #11

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.5473. Min Act: -0.0000

Data Index: 1197096 (The Pile)

Max Activating Token Index: 762

Text #12

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.5961. Min Act: -0.0000

Data Index: 784772 (The Pile)

Max Activating Token Index: 291

Text #13

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.5683. Min Act: -0.0000

Data Index: 162089 (The Pile)

Max Activating Token Index: 238

Text #14

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.6178. Min Act: -0.0000

Data Index: 1602282 (The Pile)

Max Activating Token Index: 957

Text #15

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.5324. Min Act: -0.0000

Data Index: 1284453 (The Pile)

Max Activating Token Index: 672

Text #16

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.5412. Min Act: -0.0000

Data Index: 636208 (The Pile)

Max Activating Token Index: 818

Text #17

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.5539. Min Act: -0.0000

Data Index: 1486972 (The Pile)

Max Activating Token Index: 130

Text #18

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.5128. Min Act: -0.0000

Data Index: 1108656 (The Pile)

Max Activating Token Index: 539

Text #19

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.5134. Min Act: -0.0000

Data Index: 616660 (The Pile)

Max Activating Token Index: 160