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

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

Neuron 4508 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7845. Min Range: -2.7845

Max Act: 2.7845. Min Act: -0.0000

Data Index: 1187197 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 2.7845. Min Range: -2.7845

Max Act: 2.6064. Min Act: -0.0000

Data Index: 479418 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 2.7845. Min Range: -2.7845

Max Act: 2.5849. Min Act: -0.0000

Data Index: 499028 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 2.7845. Min Range: -2.7845

Max Act: 2.6323. Min Act: -0.0000

Data Index: 79658 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 2.7845. Min Range: -2.7845

Max Act: 2.7352. Min Act: -0.0000

Data Index: 1326801 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 2.7845. Min Range: -2.7845

Max Act: 2.5469. Min Act: -0.0000

Data Index: 173927 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 2.7845. Min Range: -2.7845

Max Act: 2.5483. Min Act: -0.0000

Data Index: 652660 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 2.7845. Min Range: -2.7845

Max Act: 2.3751. Min Act: -0.0000

Data Index: 827226 (C4 (Web Text))

Max Activating Token Index: 484

Text #8

Max Range: 2.7845. Min Range: -2.7845

Max Act: 2.3916. Min Act: -0.0000

Data Index: 352342 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 2.7845. Min Range: -2.7845

Max Act: 2.4087. Min Act: -0.0000

Data Index: 865746 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 2.7845. Min Range: -2.7845

Max Act: 2.3754. Min Act: -0.0000

Data Index: 695362 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 2.7845. Min Range: -2.7845

Max Act: 2.2266. Min Act: -0.0000

Data Index: 1323408 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 2.7845. Min Range: -2.7845

Max Act: 2.2889. Min Act: -0.0000

Data Index: 570423 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 2.7845. Min Range: -2.7845

Max Act: 2.1836. Min Act: -0.0000

Data Index: 921231 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 2.7845. Min Range: -2.7845

Max Act: 2.2764. Min Act: -0.0000

Data Index: 775762 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 2.7845. Min Range: -2.7845

Max Act: 2.2741. Min Act: -0.0000

Data Index: 180829 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 2.7845. Min Range: -2.7845

Max Act: 2.3744. Min Act: -0.0000

Data Index: 454256 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 2.7845. Min Range: -2.7845

Max Act: 2.2474. Min Act: -0.0000

Data Index: 755057 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 2.7845. Min Range: -2.7845

Max Act: 2.2527. Min Act: -0.0000

Data Index: 215235 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 2.7845. Min Range: -2.7845

Max Act: 2.2502. Min Act: -0.0000

Data Index: 538071 (C4 (Web Text))

Max Activating Token Index: 354