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

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

Neuron 26 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0346. Min Act: -0.0006

Data Index: 586241 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0344. Min Act: -0.0006

Data Index: 257963 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0343. Min Act: -0.0006

Data Index: 638275 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0326. Min Act: -0.0006

Data Index: 276779 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0334. Min Act: -0.0006

Data Index: 1100115 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0326. Min Act: -0.0006

Data Index: 996547 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0341. Min Act: -0.0006

Data Index: 1074811 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0340. Min Act: -0.0006

Data Index: 179141 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0330. Min Act: -0.0006

Data Index: 1164603 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0330. Min Act: -0.0006

Data Index: 58884 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0341. Min Act: -0.0006

Data Index: 247773 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0333. Min Act: -0.0006

Data Index: 1214446 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0311. Min Act: -0.0006

Data Index: 988050 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0338. Min Act: -0.0006

Data Index: 557101 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0321. Min Act: -0.0006

Data Index: 65082 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0324. Min Act: -0.0006

Data Index: 687046 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0316. Min Act: -0.0006

Data Index: 578609 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0322. Min Act: -0.0006

Data Index: 111534 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0315. Min Act: -0.0006

Data Index: 1199759 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0314. Min Act: -0.0006

Data Index: 651900 (C4 (Web Text))

Max Activating Token Index: 723