Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2400 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0319. Min Act: -0.0001

Data Index: 1178349 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0300. Min Act: -0.0001

Data Index: 902960 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0286. Min Act: -0.0000

Data Index: 30022 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0301. Min Act: -0.0001

Data Index: 415929 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0288. Min Act: -0.0001

Data Index: 64816 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0262. Min Act: -0.0001

Data Index: 1057980 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0267. Min Act: -0.0001

Data Index: 162551 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0256. Min Act: -0.0001

Data Index: 1358433 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0261. Min Act: -0.0001

Data Index: 357082 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0260. Min Act: -0.0001

Data Index: 891068 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0243. Min Act: -0.0001

Data Index: 1192877 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0253. Min Act: -0.0001

Data Index: 982003 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0228. Min Act: -0.0001

Data Index: 22249 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0246. Min Act: -0.0001

Data Index: 334031 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0242. Min Act: -0.0001

Data Index: 383999 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0223. Min Act: -0.0001

Data Index: 311172 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0229. Min Act: -0.0001

Data Index: 348514 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0229. Min Act: -0.0001

Data Index: 64916 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0218. Min Act: -0.0001

Data Index: 1129584 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0213. Min Act: -0.0001

Data Index: 986598 (C4 (Web Text))

Max Activating Token Index: 274