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

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

Neuron 535 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0399. Min Act: -0.0005

Data Index: 1036791 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0351. Min Act: -0.0005

Data Index: 997524 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0347. Min Act: -0.0005

Data Index: 1065937 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0338. Min Act: -0.0005

Data Index: 450490 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0315. Min Act: -0.0005

Data Index: 102435 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0322. Min Act: -0.0005

Data Index: 809431 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0324. Min Act: -0.0005

Data Index: 499460 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0306. Min Act: -0.0005

Data Index: 970759 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0314. Min Act: -0.0005

Data Index: 47311 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0313. Min Act: -0.0005

Data Index: 1241964 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0311. Min Act: -0.0005

Data Index: 198413 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0320. Min Act: -0.0005

Data Index: 991529 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0311. Min Act: -0.0005

Data Index: 434728 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0301. Min Act: -0.0005

Data Index: 1089203 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0306. Min Act: -0.0005

Data Index: 358684 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0295. Min Act: -0.0005

Data Index: 1230155 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0286. Min Act: -0.0005

Data Index: 268068 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0284. Min Act: -0.0005

Data Index: 526347 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0278. Min Act: -0.0005

Data Index: 710493 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0283. Min Act: -0.0005

Data Index: 38902 (C4 (Web Text))

Max Activating Token Index: 826