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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3872 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.9437. Min Act: -0.0000

Data Index: 606654 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.9066. Min Act: -0.0000

Data Index: 46740 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.9005. Min Act: -0.0000

Data Index: 403080 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.8111. Min Act: -0.0000

Data Index: 204297 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.8585. Min Act: -0.0000

Data Index: 1027695 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.8414. Min Act: 0.0000

Data Index: 1222433 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.8577. Min Act: -0.0000

Data Index: 1226432 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.8290. Min Act: -0.0000

Data Index: 770592 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.8167. Min Act: -0.0000

Data Index: 875953 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.8181. Min Act: -0.0000

Data Index: 1025537 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.8235. Min Act: -0.0000

Data Index: 489438 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.8333. Min Act: -0.0000

Data Index: 103218 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.8099. Min Act: -0.0000

Data Index: 731744 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.7806. Min Act: -0.0000

Data Index: 79081 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.8258. Min Act: -0.0000

Data Index: 585649 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.8241. Min Act: -0.0000

Data Index: 888107 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.8182. Min Act: -0.0000

Data Index: 780906 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.7888. Min Act: -0.0000

Data Index: 857718 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.8061. Min Act: -0.0000

Data Index: 1283827 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 0.9437. Min Range: -0.9437

Max Act: 0.7847. Min Act: -0.0000

Data Index: 97666 (C4 (Web Text))

Max Activating Token Index: 505