Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3705 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0337. Min Act: -0.0002

Data Index: 396856 (C4 (Web Text))

Max Activating Token Index: 617

Text #1

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0265. Min Act: -0.0002

Data Index: 841679 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0247. Min Act: -0.0002

Data Index: 548921 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0229. Min Act: -0.0002

Data Index: 447633 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0222. Min Act: -0.0002

Data Index: 418936 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0223. Min Act: -0.0002

Data Index: 947781 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0220. Min Act: -0.0003

Data Index: 382697 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0216. Min Act: -0.0002

Data Index: 923446 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0218. Min Act: -0.0002

Data Index: 870473 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0218. Min Act: -0.0002

Data Index: 917055 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0210. Min Act: -0.0002

Data Index: 1293315 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0207. Min Act: -0.0002

Data Index: 934338 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0211. Min Act: -0.0002

Data Index: 814644 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0210. Min Act: -0.0002

Data Index: 569441 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0208. Min Act: -0.0002

Data Index: 473309 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0207. Min Act: -0.0002

Data Index: 250024 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0197. Min Act: -0.0002

Data Index: 1024626 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0203. Min Act: -0.0002

Data Index: 726954 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0204. Min Act: -0.0002

Data Index: 590847 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0201. Min Act: -0.0002

Data Index: 695169 (C4 (Web Text))

Max Activating Token Index: 207