Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 317 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0380. Min Act: -0.0006

Data Index: 828979 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0355. Min Act: -0.0006

Data Index: 1099611 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0367. Min Act: -0.0006

Data Index: 328490 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0341. Min Act: -0.0006

Data Index: 638738 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0362. Min Act: -0.0006

Data Index: 663635 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0315. Min Act: -0.0006

Data Index: 1303285 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0295. Min Act: -0.0006

Data Index: 698687 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0300. Min Act: -0.0006

Data Index: 689803 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0312. Min Act: -0.0006

Data Index: 578565 (C4 (Web Text))

Max Activating Token Index: 964

Text #9

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0311. Min Act: -0.0006

Data Index: 170003 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0295. Min Act: -0.0006

Data Index: 1230659 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0295. Min Act: -0.0006

Data Index: 587769 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0321. Min Act: -0.0006

Data Index: 291727 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0301. Min Act: -0.0006

Data Index: 417734 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0299. Min Act: -0.0006

Data Index: 1222997 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0287. Min Act: -0.0006

Data Index: 56152 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0292. Min Act: -0.0006

Data Index: 961681 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0297. Min Act: -0.0006

Data Index: 798009 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0284. Min Act: -0.0006

Data Index: 898727 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0290. Min Act: -0.0006

Data Index: 61841 (C4 (Web Text))

Max Activating Token Index: 1013