Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5213 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.8724. Min Act: -0.0000

Data Index: 669106 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.7397. Min Act: -0.0000

Data Index: 1212599 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6974. Min Act: -0.0000

Data Index: 151477 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6549. Min Act: -0.0000

Data Index: 419974 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.6858. Min Act: -0.0000

Data Index: 436763 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.5632. Min Act: -0.0000

Data Index: 808379 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.5744. Min Act: -0.0000

Data Index: 998472 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.5700. Min Act: -0.0000

Data Index: 283311 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.5440. Min Act: -0.0000

Data Index: 1197566 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.5273. Min Act: -0.0000

Data Index: 1023502 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.5578. Min Act: -0.0000

Data Index: 1344723 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.5199. Min Act: -0.0000

Data Index: 144320 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.5586. Min Act: -0.0000

Data Index: 191775 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.5509. Min Act: -0.0000

Data Index: 274724 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.5160. Min Act: -0.0000

Data Index: 1033590 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.4953. Min Act: -0.0000

Data Index: 643858 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.5136. Min Act: -0.0000

Data Index: 1522037 (Python Code)

Max Activating Token Index: 21

Text #17

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.5237. Min Act: -0.0000

Data Index: 658194 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.4352. Min Act: -0.0000

Data Index: 891068 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 0.8724. Min Range: -0.8724

Max Act: 0.5230. Min Act: -0.0000

Data Index: 451767 (C4 (Web Text))

Max Activating Token Index: 491