Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1456 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0300. Min Act: -0.0003

Data Index: 953434 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0311. Min Act: -0.0004

Data Index: 317598 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0307. Min Act: -0.0003

Data Index: 445740 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0304. Min Act: -0.0003

Data Index: 846878 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0313. Min Act: -0.0002

Data Index: 272925 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0310. Min Act: -0.0003

Data Index: 1126945 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0301. Min Act: -0.0002

Data Index: 1069572 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0298. Min Act: -0.0004

Data Index: 629298 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0297. Min Act: -0.0003

Data Index: 277774 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0294. Min Act: -0.0003

Data Index: 504045 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0300. Min Act: -0.0003

Data Index: 804774 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0286. Min Act: -0.0002

Data Index: 41174 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0289. Min Act: -0.0003

Data Index: 1157314 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0278. Min Act: -0.0003

Data Index: 1132684 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0280. Min Act: -0.0004

Data Index: 1059520 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0283. Min Act: -0.0003

Data Index: 1059111 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0273. Min Act: -0.0004

Data Index: 607200 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0277. Min Act: -0.0003

Data Index: 1220150 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0274. Min Act: -0.0003

Data Index: 750962 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0278. Min Act: -0.0002

Data Index: 1007186 (C4 (Web Text))

Max Activating Token Index: 1014