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

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

Neuron 3028 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5411. Min Range: -0.5411

Max Act: 0.5230. Min Act: -0.0000

Data Index: 552783 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.5411. Min Range: -0.5411

Max Act: 0.5202. Min Act: -0.0000

Data Index: 1229327 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 0.5411. Min Range: -0.5411

Max Act: 0.4672. Min Act: -0.0000

Data Index: 823517 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 0.5411. Min Range: -0.5411

Max Act: 0.5411. Min Act: -0.0000

Data Index: 667958 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 0.5411. Min Range: -0.5411

Max Act: 0.4561. Min Act: -0.0000

Data Index: 241234 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.5411. Min Range: -0.5411

Max Act: 0.3903. Min Act: -0.0000

Data Index: 618587 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 0.5411. Min Range: -0.5411

Max Act: 0.4225. Min Act: -0.0000

Data Index: 914599 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 0.5411. Min Range: -0.5411

Max Act: 0.4363. Min Act: -0.0000

Data Index: 721566 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 0.5411. Min Range: -0.5411

Max Act: 0.3942. Min Act: -0.0000

Data Index: 213059 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.5411. Min Range: -0.5411

Max Act: 0.4019. Min Act: -0.0000

Data Index: 1118746 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 0.5411. Min Range: -0.5411

Max Act: 0.4132. Min Act: -0.0000

Data Index: 412681 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 0.5411. Min Range: -0.5411

Max Act: 0.3914. Min Act: 0.0001

Data Index: 1264204 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 0.5411. Min Range: -0.5411

Max Act: 0.3905. Min Act: -0.0000

Data Index: 1046038 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 0.5411. Min Range: -0.5411

Max Act: 0.3875. Min Act: -0.0000

Data Index: 1319540 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 0.5411. Min Range: -0.5411

Max Act: 0.4050. Min Act: -0.0000

Data Index: 299454 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 0.5411. Min Range: -0.5411

Max Act: 0.3592. Min Act: 0.0001

Data Index: 497874 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 0.5411. Min Range: -0.5411

Max Act: 0.3431. Min Act: -0.0000

Data Index: 1339497 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 0.5411. Min Range: -0.5411

Max Act: 0.3755. Min Act: -0.0000

Data Index: 475265 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 0.5411. Min Range: -0.5411

Max Act: 0.3605. Min Act: -0.0000

Data Index: 547766 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 0.5411. Min Range: -0.5411

Max Act: 0.3435. Min Act: -0.0000

Data Index: 878395 (C4 (Web Text))

Max Activating Token Index: 964