Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 378 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0357. Min Act: -0.0003

Data Index: 1015272 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0339. Min Act: -0.0003

Data Index: 714518 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0339. Min Act: -0.0003

Data Index: 505482 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0318. Min Act: -0.0003

Data Index: 283757 (C4 (Web Text))

Max Activating Token Index: 975

Text #4

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0307. Min Act: -0.0003

Data Index: 204084 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0297. Min Act: -0.0003

Data Index: 16395 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0294. Min Act: -0.0003

Data Index: 102069 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0287. Min Act: -0.0003

Data Index: 530559 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0297. Min Act: -0.0003

Data Index: 1319706 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0282. Min Act: -0.0003

Data Index: 252381 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0284. Min Act: -0.0003

Data Index: 922023 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0295. Min Act: -0.0004

Data Index: 1290370 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0288. Min Act: -0.0003

Data Index: 1035176 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1132729 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0271. Min Act: -0.0003

Data Index: 1084151 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0277. Min Act: -0.0003

Data Index: 1168196 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0283. Min Act: -0.0003

Data Index: 955469 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0279. Min Act: -0.0003

Data Index: 195040 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0271. Min Act: -0.0003

Data Index: 1290847 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0276. Min Act: -0.0004

Data Index: 167456 (C4 (Web Text))

Max Activating Token Index: 75