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

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

Neuron 2652 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: 0.0322. Min Range: -0.0322

Max Act: 0.0322. Min Act: -0.0001

Data Index: 1029835 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0311. Min Act: -0.0001

Data Index: 1269475 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0267. Min Act: -0.0001

Data Index: 235630 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0260. Min Act: -0.0001

Data Index: 965580 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0251. Min Act: -0.0001

Data Index: 514414 (C4 (Web Text))

Max Activating Token Index: 983

Text #5

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0249. Min Act: -0.0001

Data Index: 438623 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0251. Min Act: -0.0001

Data Index: 429307 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0234. Min Act: -0.0001

Data Index: 118586 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0252. Min Act: -0.0001

Data Index: 350525 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0246. Min Act: -0.0001

Data Index: 1259671 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0246. Min Act: -0.0001

Data Index: 891424 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0239. Min Act: -0.0001

Data Index: 1080158 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0237. Min Act: -0.0001

Data Index: 589923 (C4 (Web Text))

Max Activating Token Index: 949

Text #13

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0233. Min Act: -0.0001

Data Index: 1242314 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0236. Min Act: -0.0001

Data Index: 513982 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0223. Min Act: -0.0001

Data Index: 550807 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0224. Min Act: -0.0001

Data Index: 1282335 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0220. Min Act: -0.0001

Data Index: 795329 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0218. Min Act: -0.0001

Data Index: 415012 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.0322. Min Range: -0.0322

Max Act: 0.0216. Min Act: -0.0001

Data Index: 407325 (C4 (Web Text))

Max Activating Token Index: 604