Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5025 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0519. Min Act: -0.0003

Data Index: 245035 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0420. Min Act: -0.0003

Data Index: 861040 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0419. Min Act: -0.0003

Data Index: 75777 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0381. Min Act: -0.0002

Data Index: 1223866 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0375. Min Act: -0.0002

Data Index: 151096 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0372. Min Act: -0.0003

Data Index: 1186258 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0368. Min Act: -0.0003

Data Index: 28654 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0376. Min Act: -0.0003

Data Index: 1160183 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0357. Min Act: -0.0003

Data Index: 636914 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0349. Min Act: -0.0003

Data Index: 408450 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0339. Min Act: -0.0002

Data Index: 614550 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0343. Min Act: -0.0002

Data Index: 679542 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0339. Min Act: -0.0003

Data Index: 378042 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0339. Min Act: -0.0003

Data Index: 439059 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0328. Min Act: -0.0003

Data Index: 244741 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0334. Min Act: -0.0003

Data Index: 672983 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0317. Min Act: -0.0003

Data Index: 884468 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0314. Min Act: -0.0002

Data Index: 909560 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0305. Min Act: -0.0003

Data Index: 297094 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 0.0519. Min Range: -0.0519

Max Act: 0.0310. Min Act: -0.0003

Data Index: 571719 (C4 (Web Text))

Max Activating Token Index: 418