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

Dataset: The Pile

Neuron 2135 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3437. Min Range: -1.3437

Max Act: 1.3437. Min Act: -0.0000

Data Index: 1793028 (The Pile)

Max Activating Token Index: 362

Text #1

Max Range: 1.3437. Min Range: -1.3437

Max Act: 1.1252. Min Act: -0.0000

Data Index: 619357 (The Pile)

Max Activating Token Index: 671

Text #2

Max Range: 1.3437. Min Range: -1.3437

Max Act: 1.1629. Min Act: -0.0000

Data Index: 1553665 (The Pile)

Max Activating Token Index: 350

Text #3

Max Range: 1.3437. Min Range: -1.3437

Max Act: 0.9687. Min Act: -0.0000

Data Index: 673520 (The Pile)

Max Activating Token Index: 367

Text #4

Max Range: 1.3437. Min Range: -1.3437

Max Act: 0.9670. Min Act: -0.0000

Data Index: 796402 (The Pile)

Max Activating Token Index: 198

Text #5

Max Range: 1.3437. Min Range: -1.3437

Max Act: 0.8774. Min Act: -0.0000

Data Index: 463245 (The Pile)

Max Activating Token Index: 702

Text #6

Max Range: 1.3437. Min Range: -1.3437

Max Act: 0.8896. Min Act: -0.0000

Data Index: 415254 (The Pile)

Max Activating Token Index: 489

Text #7

Max Range: 1.3437. Min Range: -1.3437

Max Act: 0.8725. Min Act: -0.0000

Data Index: 871037 (The Pile)

Max Activating Token Index: 105

Text #8

Max Range: 1.3437. Min Range: -1.3437

Max Act: 0.8622. Min Act: -0.0000

Data Index: 1488850 (The Pile)

Max Activating Token Index: 1007

Text #9

Max Range: 1.3437. Min Range: -1.3437

Max Act: 0.7981. Min Act: -0.0000

Data Index: 786480 (The Pile)

Max Activating Token Index: 552

Text #10

Max Range: 1.3437. Min Range: -1.3437

Max Act: 0.7955. Min Act: -0.0000

Data Index: 956220 (The Pile)

Max Activating Token Index: 13

Text #11

Max Range: 1.3437. Min Range: -1.3437

Max Act: 0.8616. Min Act: -0.0000

Data Index: 1980757 (The Pile)

Max Activating Token Index: 370

Text #12

Max Range: 1.3437. Min Range: -1.3437

Max Act: 0.7813. Min Act: -0.0000

Data Index: 1885688 (The Pile)

Max Activating Token Index: 642

Text #13

Max Range: 1.3437. Min Range: -1.3437

Max Act: 0.8249. Min Act: -0.0000

Data Index: 675248 (The Pile)

Max Activating Token Index: 9

Text #14

Max Range: 1.3437. Min Range: -1.3437

Max Act: 0.6950. Min Act: -0.0000

Data Index: 1937076 (The Pile)

Max Activating Token Index: 747

Text #15

Max Range: 1.3437. Min Range: -1.3437

Max Act: 0.7272. Min Act: -0.0000

Data Index: 80244 (The Pile)

Max Activating Token Index: 897

Text #16

Max Range: 1.3437. Min Range: -1.3437

Max Act: 0.8823. Min Act: -0.0000

Data Index: 1490227 (The Pile)

Max Activating Token Index: 381

Text #17

Max Range: 1.3437. Min Range: -1.3437

Max Act: 0.7934. Min Act: -0.0000

Data Index: 59212 (The Pile)

Max Activating Token Index: 12

Text #18

Max Range: 1.3437. Min Range: -1.3437

Max Act: 0.7509. Min Act: -0.0000

Data Index: 1050539 (The Pile)

Max Activating Token Index: 585

Text #19

Max Range: 1.3437. Min Range: -1.3437

Max Act: 0.7661. Min Act: -0.0000

Data Index: 540136 (The Pile)

Max Activating Token Index: 6