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

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

Neuron 4730 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: 0.6385. Min Range: -0.6385

Max Act: 0.6381. Min Act: -0.0000

Data Index: 895325 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.6310. Min Act: -0.0000

Data Index: 696503 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.6385. Min Act: -0.0000

Data Index: 1187130 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.6204. Min Act: -0.0000

Data Index: 547750 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.6142. Min Act: -0.0000

Data Index: 863979 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.5620. Min Act: 0.0000

Data Index: 549717 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.5949. Min Act: -0.0000

Data Index: 1006130 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.5838. Min Act: -0.0000

Data Index: 419198 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.5678. Min Act: -0.0000

Data Index: 937561 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.5380. Min Act: 0.0000

Data Index: 1137164 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.5345. Min Act: -0.0000

Data Index: 193641 (C4 (Web Text))

Max Activating Token Index: 351

Text #11

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.5513. Min Act: -0.0000

Data Index: 137088 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.5043. Min Act: -0.0000

Data Index: 313522 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.5066. Min Act: -0.0000

Data Index: 1106270 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.5076. Min Act: -0.0000

Data Index: 887342 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4878. Min Act: -0.0000

Data Index: 497423 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.5122. Min Act: -0.0000

Data Index: 1134398 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4913. Min Act: -0.0000

Data Index: 1082585 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4813. Min Act: -0.0000

Data Index: 388184 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 0.6385. Min Range: -0.6385

Max Act: 0.4808. Min Act: 0.0000

Data Index: 319145 (C4 (Web Text))

Max Activating Token Index: 86