Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3006 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0332. Min Act: -0.0001

Data Index: 1183192 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0339. Min Act: -0.0001

Data Index: 1311261 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0344. Min Act: -0.0001

Data Index: 448695 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0303. Min Act: -0.0001

Data Index: 1108879 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0310. Min Act: -0.0001

Data Index: 1103023 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0337. Min Act: -0.0001

Data Index: 226337 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0318. Min Act: -0.0001

Data Index: 749049 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0330. Min Act: -0.0001

Data Index: 779529 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0315. Min Act: -0.0001

Data Index: 1272636 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0302. Min Act: -0.0001

Data Index: 936322 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0283. Min Act: -0.0001

Data Index: 448611 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0285. Min Act: -0.0001

Data Index: 343876 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0300. Min Act: -0.0001

Data Index: 1468364 (Python Code)

Max Activating Token Index: 786

Text #13

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0304. Min Act: -0.0001

Data Index: 1299155 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0292. Min Act: -0.0001

Data Index: 1239402 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0273. Min Act: -0.0001

Data Index: 988966 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0291. Min Act: -0.0001

Data Index: 307138 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0297. Min Act: -0.0001

Data Index: 802029 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0314. Min Act: -0.0001

Data Index: 688032 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0297. Min Act: -0.0001

Data Index: 1220548 (C4 (Web Text))

Max Activating Token Index: 574