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

Dataset: The Pile

Neuron 896 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.4680. Min Act: -0.0000

Data Index: 1756591 (The Pile)

Max Activating Token Index: 503

Text #1

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.4635. Min Act: -0.0000

Data Index: 346546 (The Pile)

Max Activating Token Index: 776

Text #2

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.5459. Min Act: -0.0000

Data Index: 1874060 (The Pile)

Max Activating Token Index: 1001

Text #3

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.3662. Min Act: -0.0000

Data Index: 140149 (The Pile)

Max Activating Token Index: 669

Text #4

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.3712. Min Act: -0.0000

Data Index: 505237 (The Pile)

Max Activating Token Index: 351

Text #5

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.4991. Min Act: -0.0000

Data Index: 959319 (The Pile)

Max Activating Token Index: 112

Text #6

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.3292. Min Act: -0.0000

Data Index: 1170364 (The Pile)

Max Activating Token Index: 811

Text #7

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.3033. Min Act: -0.0000

Data Index: 362621 (The Pile)

Max Activating Token Index: 560

Text #8

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.3273. Min Act: -0.0000

Data Index: 1341547 (The Pile)

Max Activating Token Index: 637

Text #9

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.4234. Min Act: -0.0000

Data Index: 1730309 (The Pile)

Max Activating Token Index: 684

Text #10

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.3553. Min Act: -0.0000

Data Index: 1024386 (The Pile)

Max Activating Token Index: 279

Text #11

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.3191. Min Act: -0.0000

Data Index: 550841 (The Pile)

Max Activating Token Index: 30

Text #12

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.2793. Min Act: -0.0000

Data Index: 1431532 (The Pile)

Max Activating Token Index: 931

Text #13

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.2491. Min Act: -0.0000

Data Index: 1856800 (The Pile)

Max Activating Token Index: 53

Text #14

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.3661. Min Act: -0.0000

Data Index: 764869 (The Pile)

Max Activating Token Index: 281

Text #15

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.3920. Min Act: -0.0000

Data Index: 1270656 (The Pile)

Max Activating Token Index: 741

Text #16

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.3427. Min Act: -0.0000

Data Index: 357370 (The Pile)

Max Activating Token Index: 527

Text #17

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.2282. Min Act: -0.0000

Data Index: 1126146 (The Pile)

Max Activating Token Index: 988

Text #18

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.2168. Min Act: -0.0000

Data Index: 406094 (The Pile)

Max Activating Token Index: 59

Text #19

Max Range: 1.5459. Min Range: -1.5459

Max Act: 1.2028. Min Act: -0.0000

Data Index: 118158 (The Pile)

Max Activating Token Index: 18