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

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

Neuron 4972 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4212. Min Range: -1.4212

Max Act: 1.3480. Min Act: -0.0001

Data Index: 507271 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 1.4212. Min Range: -1.4212

Max Act: 1.4212. Min Act: -0.0001

Data Index: 923707 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 1.4212. Min Range: -1.4212

Max Act: 1.2938. Min Act: -0.0001

Data Index: 562199 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 1.4212. Min Range: -1.4212

Max Act: 1.2888. Min Act: -0.0001

Data Index: 253502 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 1.4212. Min Range: -1.4212

Max Act: 1.3123. Min Act: -0.0001

Data Index: 236945 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 1.4212. Min Range: -1.4212

Max Act: 1.2147. Min Act: -0.0001

Data Index: 699406 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 1.4212. Min Range: -1.4212

Max Act: 1.2521. Min Act: -0.0001

Data Index: 494468 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 1.4212. Min Range: -1.4212

Max Act: 1.2145. Min Act: -0.0001

Data Index: 1085662 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 1.4212. Min Range: -1.4212

Max Act: 1.2156. Min Act: -0.0001

Data Index: 1134888 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 1.4212. Min Range: -1.4212

Max Act: 1.1206. Min Act: -0.0001

Data Index: 1159383 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 1.4212. Min Range: -1.4212

Max Act: 1.1801. Min Act: -0.0001

Data Index: 48843 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 1.4212. Min Range: -1.4212

Max Act: 1.0615. Min Act: -0.0001

Data Index: 91842 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 1.4212. Min Range: -1.4212

Max Act: 1.1502. Min Act: -0.0001

Data Index: 362045 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 1.4212. Min Range: -1.4212

Max Act: 1.1770. Min Act: -0.0001

Data Index: 937760 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 1.4212. Min Range: -1.4212

Max Act: 1.0665. Min Act: -0.0001

Data Index: 976875 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 1.4212. Min Range: -1.4212

Max Act: 1.0588. Min Act: -0.0001

Data Index: 510188 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 1.4212. Min Range: -1.4212

Max Act: 1.1208. Min Act: -0.0001

Data Index: 18378 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 1.4212. Min Range: -1.4212

Max Act: 1.0738. Min Act: -0.0001

Data Index: 370395 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 1.4212. Min Range: -1.4212

Max Act: 1.0824. Min Act: -0.0001

Data Index: 411582 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 1.4212. Min Range: -1.4212

Max Act: 0.9614. Min Act: -0.0001

Data Index: 965424 (C4 (Web Text))

Max Activating Token Index: 276