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

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

Neuron 612 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2307. Min Range: -1.2307

Max Act: 1.2307. Min Act: -0.0001

Data Index: 546176 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 1.2307. Min Range: -1.2307

Max Act: 1.0440. Min Act: -0.0001

Data Index: 1184427 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 1.2307. Min Range: -1.2307

Max Act: 1.1314. Min Act: -0.0001

Data Index: 812670 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 1.2307. Min Range: -1.2307

Max Act: 1.0150. Min Act: -0.0001

Data Index: 573148 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 1.2307. Min Range: -1.2307

Max Act: 1.0427. Min Act: -0.0001

Data Index: 65772 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 1.2307. Min Range: -1.2307

Max Act: 1.0280. Min Act: -0.0001

Data Index: 100667 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 1.2307. Min Range: -1.2307

Max Act: 1.0314. Min Act: -0.0001

Data Index: 598427 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.9294. Min Act: -0.0001

Data Index: 230880 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.9187. Min Act: -0.0001

Data Index: 1117814 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.9959. Min Act: -0.0001

Data Index: 115165 (C4 (Web Text))

Max Activating Token Index: 1012

Text #10

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.9070. Min Act: -0.0001

Data Index: 1284487 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.8813. Min Act: -0.0001

Data Index: 31524 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.9154. Min Act: -0.0001

Data Index: 427610 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.8794. Min Act: -0.0001

Data Index: 530370 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.8366. Min Act: -0.0001

Data Index: 860287 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.8925. Min Act: -0.0001

Data Index: 142081 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.8597. Min Act: -0.0001

Data Index: 887816 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.8678. Min Act: -0.0001

Data Index: 122635 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.8935. Min Act: -0.0001

Data Index: 1245136 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 1.2307. Min Range: -1.2307

Max Act: 0.8828. Min Act: -0.0001

Data Index: 361081 (C4 (Web Text))

Max Activating Token Index: 617