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

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

Neuron 1993 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: 0.0355. Min Range: -0.0355

Max Act: 0.0352. Min Act: -0.0005

Data Index: 542406 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0351. Min Act: -0.0005

Data Index: 794537 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0355. Min Act: -0.0005

Data Index: 1225167 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0335. Min Act: -0.0005

Data Index: 164322 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0335. Min Act: -0.0005

Data Index: 228587 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0329. Min Act: -0.0005

Data Index: 344168 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0323. Min Act: -0.0005

Data Index: 1354199 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0332. Min Act: -0.0005

Data Index: 246236 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0310. Min Act: -0.0005

Data Index: 161063 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0308. Min Act: -0.0005

Data Index: 505553 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0313. Min Act: -0.0005

Data Index: 86906 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0292. Min Act: -0.0005

Data Index: 714700 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0314. Min Act: -0.0005

Data Index: 1193248 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0307. Min Act: -0.0005

Data Index: 1004663 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0297. Min Act: -0.0005

Data Index: 128263 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0315. Min Act: -0.0005

Data Index: 1280915 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0297. Min Act: -0.0005

Data Index: 164408 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0304. Min Act: -0.0005

Data Index: 918004 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0301. Min Act: -0.0005

Data Index: 36866 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0298. Min Act: -0.0005

Data Index: 5981 (C4 (Web Text))

Max Activating Token Index: 560