Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1236 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.4197. Min Act: -0.0000

Data Index: 396990 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.4089. Min Act: -0.0000

Data Index: 1275394 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.3535. Min Act: -0.0000

Data Index: 943629 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.3647. Min Act: -0.0000

Data Index: 549890 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.3314. Min Act: -0.0000

Data Index: 561093 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.3347. Min Act: -0.0000

Data Index: 70955 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.3236. Min Act: -0.0000

Data Index: 226497 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.3216. Min Act: -0.0000

Data Index: 233139 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.3226. Min Act: -0.0000

Data Index: 303489 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.3212. Min Act: -0.0000

Data Index: 932325 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.3046. Min Act: -0.0000

Data Index: 1004803 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.3163. Min Act: -0.0000

Data Index: 750552 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.2961. Min Act: -0.0000

Data Index: 287774 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.3035. Min Act: -0.0000

Data Index: 918712 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.2954. Min Act: -0.0000

Data Index: 844998 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.3008. Min Act: -0.0000

Data Index: 906255 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.2829. Min Act: -0.0000

Data Index: 1252947 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.2921. Min Act: -0.0000

Data Index: 481436 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.2720. Min Act: -0.0000

Data Index: 690273 (C4 (Web Text))

Max Activating Token Index: 881

Text #19

Max Range: 0.4197. Min Range: -0.4197

Max Act: 0.2738. Min Act: -0.0000

Data Index: 597 (C4 (Web Text))

Max Activating Token Index: 867