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

Dataset: The Pile

Neuron 1877 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.4437. Min Act: -0.0000

Data Index: 1822091 (The Pile)

Max Activating Token Index: 906

Text #1

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3911. Min Act: -0.0000

Data Index: 419745 (The Pile)

Max Activating Token Index: 543

Text #2

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3587. Min Act: -0.0000

Data Index: 1500326 (The Pile)

Max Activating Token Index: 934

Text #3

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3475. Min Act: -0.0000

Data Index: 805256 (The Pile)

Max Activating Token Index: 834

Text #4

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3644. Min Act: 0.0000

Data Index: 376344 (The Pile)

Max Activating Token Index: 983

Text #5

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3270. Min Act: -0.0000

Data Index: 909126 (The Pile)

Max Activating Token Index: 793

Text #6

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3188. Min Act: -0.0000

Data Index: 1100888 (The Pile)

Max Activating Token Index: 356

Text #7

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3129. Min Act: 0.0001

Data Index: 372894 (The Pile)

Max Activating Token Index: 462

Text #8

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3286. Min Act: -0.0000

Data Index: 748144 (The Pile)

Max Activating Token Index: 782

Text #9

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3205. Min Act: -0.0000

Data Index: 1588528 (The Pile)

Max Activating Token Index: 947

Text #10

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.2904. Min Act: -0.0000

Data Index: 417663 (The Pile)

Max Activating Token Index: 727

Text #11

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.2840. Min Act: -0.0000

Data Index: 1684589 (The Pile)

Max Activating Token Index: 661

Text #12

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3220. Min Act: -0.0000

Data Index: 196342 (The Pile)

Max Activating Token Index: 472

Text #13

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3236. Min Act: -0.0000

Data Index: 1167666 (The Pile)

Max Activating Token Index: 207

Text #14

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.3157. Min Act: -0.0000

Data Index: 484245 (The Pile)

Max Activating Token Index: 256

Text #15

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.2863. Min Act: -0.0000

Data Index: 1329782 (The Pile)

Max Activating Token Index: 639

Text #16

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.2691. Min Act: -0.0000

Data Index: 509181 (The Pile)

Max Activating Token Index: 642

Text #17

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.2878. Min Act: -0.0000

Data Index: 1832009 (The Pile)

Max Activating Token Index: 819

Text #18

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.2803. Min Act: 0.0000

Data Index: 1523487 (The Pile)

Max Activating Token Index: 949

Text #19

Max Range: 0.4437. Min Range: -0.4437

Max Act: 0.2814. Min Act: -0.0000

Data Index: 1167610 (The Pile)

Max Activating Token Index: 1007