Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 384 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0374. Min Act: -0.0005

Data Index: 8170 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0384. Min Act: -0.0005

Data Index: 1261028 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0361. Min Act: -0.0005

Data Index: 532555 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0345. Min Act: -0.0005

Data Index: 276074 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0337. Min Act: -0.0005

Data Index: 1359260 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0346. Min Act: -0.0005

Data Index: 43886 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0321. Min Act: -0.0005

Data Index: 1006816 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0333. Min Act: -0.0005

Data Index: 1159958 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0318. Min Act: -0.0005

Data Index: 1079059 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0313. Min Act: -0.0005

Data Index: 221265 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0339. Min Act: -0.0005

Data Index: 310597 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0326. Min Act: -0.0005

Data Index: 1223179 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0315. Min Act: -0.0005

Data Index: 386430 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0304. Min Act: -0.0005

Data Index: 56777 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0301. Min Act: -0.0005

Data Index: 275281 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0309. Min Act: -0.0005

Data Index: 432590 (C4 (Web Text))

Max Activating Token Index: 706

Text #16

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0301. Min Act: -0.0005

Data Index: 604730 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0287. Min Act: -0.0005

Data Index: 1348701 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0281. Min Act: -0.0005

Data Index: 904039 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 0.0384. Min Range: -0.0384

Max Act: 0.0297. Min Act: -0.0005

Data Index: 1203562 (C4 (Web Text))

Max Activating Token Index: 926