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

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

Neuron 1775 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0366. Min Act: -0.0006

Data Index: 67308 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0334. Min Act: -0.0006

Data Index: 1200873 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0325. Min Act: -0.0006

Data Index: 859129 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0321. Min Act: -0.0006

Data Index: 709186 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0299. Min Act: -0.0006

Data Index: 997594 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0297. Min Act: -0.0006

Data Index: 1322097 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0306. Min Act: -0.0005

Data Index: 476031 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0286. Min Act: -0.0006

Data Index: 192024 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0297. Min Act: -0.0006

Data Index: 1265915 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0292. Min Act: -0.0006

Data Index: 309759 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0289. Min Act: -0.0006

Data Index: 1240331 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0286. Min Act: -0.0006

Data Index: 783735 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0273. Min Act: -0.0006

Data Index: 448070 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0283. Min Act: -0.0006

Data Index: 731162 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0283. Min Act: -0.0006

Data Index: 539409 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0283. Min Act: -0.0006

Data Index: 372234 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0288. Min Act: -0.0006

Data Index: 1004948 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0273. Min Act: -0.0006

Data Index: 1136846 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0273. Min Act: -0.0006

Data Index: 1199041 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 0.0366. Min Range: -0.0366

Max Act: 0.0283. Min Act: -0.0006

Data Index: 1258773 (C4 (Web Text))

Max Activating Token Index: 729