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

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

Neuron 171 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.3216. Min Act: -0.0001

Data Index: 773915 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 1.3216. Min Range: -1.3216

Max Act: 0.9960. Min Act: -0.0000

Data Index: 470745 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.0038. Min Act: -0.0000

Data Index: 682934 (C4 (Web Text))

Max Activating Token Index: 602

Text #3

Max Range: 1.3216. Min Range: -1.3216

Max Act: 0.9988. Min Act: -0.0000

Data Index: 1186889 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 1.3216. Min Range: -1.3216

Max Act: 0.9887. Min Act: -0.0000

Data Index: 557361 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 1.3216. Min Range: -1.3216

Max Act: 0.9758. Min Act: -0.0000

Data Index: 1284992 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 1.3216. Min Range: -1.3216

Max Act: 0.9991. Min Act: -0.0000

Data Index: 130102 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 1.3216. Min Range: -1.3216

Max Act: 0.9315. Min Act: -0.0000

Data Index: 739170 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 1.3216. Min Range: -1.3216

Max Act: 1.0176. Min Act: -0.0000

Data Index: 848232 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 1.3216. Min Range: -1.3216

Max Act: 0.9134. Min Act: -0.0000

Data Index: 353742 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 1.3216. Min Range: -1.3216

Max Act: 0.9180. Min Act: -0.0000

Data Index: 1167879 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 1.3216. Min Range: -1.3216

Max Act: 0.9688. Min Act: -0.0000

Data Index: 1175643 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 1.3216. Min Range: -1.3216

Max Act: 0.9324. Min Act: -0.0000

Data Index: 662306 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 1.3216. Min Range: -1.3216

Max Act: 0.9176. Min Act: -0.0000

Data Index: 614027 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 1.3216. Min Range: -1.3216

Max Act: 0.9397. Min Act: -0.0000

Data Index: 67501 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 1.3216. Min Range: -1.3216

Max Act: 0.8971. Min Act: -0.0000

Data Index: 139991 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 1.3216. Min Range: -1.3216

Max Act: 0.8255. Min Act: -0.0001

Data Index: 261035 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 1.3216. Min Range: -1.3216

Max Act: 0.8749. Min Act: -0.0001

Data Index: 576936 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 1.3216. Min Range: -1.3216

Max Act: 0.8764. Min Act: -0.0000

Data Index: 117864 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 1.3216. Min Range: -1.3216

Max Act: 0.8707. Min Act: -0.0000

Data Index: 343103 (C4 (Web Text))

Max Activating Token Index: 288