Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2551 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0276. Min Act: -0.0003

Data Index: 1043927 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0279. Min Act: -0.0003

Data Index: 1255144 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0268. Min Act: -0.0003

Data Index: 1234126 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0265. Min Act: -0.0003

Data Index: 1020552 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0231. Min Act: -0.0003

Data Index: 563275 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0260. Min Act: -0.0003

Data Index: 587368 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0237. Min Act: -0.0003

Data Index: 146312 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0235. Min Act: -0.0003

Data Index: 560239 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0240. Min Act: -0.0003

Data Index: 1182544 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0239. Min Act: -0.0003

Data Index: 722 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0239. Min Act: -0.0003

Data Index: 1497945 (Python Code)

Max Activating Token Index: 575

Text #11

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0212. Min Act: -0.0003

Data Index: 1233195 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0228. Min Act: -0.0003

Data Index: 1215507 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0242. Min Act: -0.0003

Data Index: 1099124 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0232. Min Act: -0.0003

Data Index: 1497099 (Python Code)

Max Activating Token Index: 116

Text #15

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0215. Min Act: -0.0003

Data Index: 383595 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0230. Min Act: -0.0003

Data Index: 554257 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0233. Min Act: -0.0003

Data Index: 1435708 (Python Code)

Max Activating Token Index: 1011

Text #18

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0229. Min Act: -0.0003

Data Index: 1373787 (Python Code)

Max Activating Token Index: 190

Text #19

Max Range: 0.0279. Min Range: -0.0279

Max Act: 0.0229. Min Act: -0.0003

Data Index: 437553 (C4 (Web Text))

Max Activating Token Index: 128