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

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

Neuron 4 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4201. Min Range: -1.4201

Max Act: 1.4201. Min Act: -0.0001

Data Index: 924711 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 1.4201. Min Range: -1.4201

Max Act: 1.2113. Min Act: -0.0001

Data Index: 26427 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 1.4201. Min Range: -1.4201

Max Act: 1.1117. Min Act: -0.0001

Data Index: 22410 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 1.4201. Min Range: -1.4201

Max Act: 1.1013. Min Act: -0.0001

Data Index: 515420 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 1.4201. Min Range: -1.4201

Max Act: 1.0364. Min Act: -0.0001

Data Index: 1300308 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 1.4201. Min Range: -1.4201

Max Act: 1.0002. Min Act: -0.0001

Data Index: 1281546 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 1.4201. Min Range: -1.4201

Max Act: 1.0532. Min Act: -0.0001

Data Index: 1314390 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 1.4201. Min Range: -1.4201

Max Act: 1.0433. Min Act: -0.0001

Data Index: 701443 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.9823. Min Act: -0.0001

Data Index: 598802 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.9343. Min Act: -0.0001

Data Index: 1186985 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.9325. Min Act: -0.0001

Data Index: 328761 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.9397. Min Act: -0.0001

Data Index: 665564 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.9152. Min Act: -0.0001

Data Index: 1305639 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.8717. Min Act: -0.0001

Data Index: 103471 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.9428. Min Act: -0.0001

Data Index: 1141570 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.9182. Min Act: -0.0001

Data Index: 389982 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.8564. Min Act: -0.0001

Data Index: 681650 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.8113. Min Act: -0.0001

Data Index: 878092 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.9767. Min Act: -0.0001

Data Index: 513988 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.8823. Min Act: -0.0001

Data Index: 724352 (C4 (Web Text))

Max Activating Token Index: 211