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

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

Neuron 3286 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.6054. Min Act: -0.0000

Data Index: 97418 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.3197. Min Act: -0.0000

Data Index: 225248 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.3501. Min Act: -0.0000

Data Index: 38213 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.0832. Min Act: -0.0000

Data Index: 409640 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.0946. Min Act: -0.0000

Data Index: 933946 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.1382. Min Act: -0.0000

Data Index: 1292049 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.0204. Min Act: 0.0000

Data Index: 736429 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.0326. Min Act: 0.0000

Data Index: 340364 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 1.6054. Min Range: -1.6054

Max Act: 0.9750. Min Act: -0.0000

Data Index: 711240 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.0701. Min Act: -0.0000

Data Index: 149196 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.0332. Min Act: -0.0000

Data Index: 1208664 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 1.6054. Min Range: -1.6054

Max Act: 0.8811. Min Act: -0.0000

Data Index: 1272002 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 1.6054. Min Range: -1.6054

Max Act: 0.9156. Min Act: -0.0000

Data Index: 1155094 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 1.6054. Min Range: -1.6054

Max Act: 0.9161. Min Act: -0.0000

Data Index: 1355293 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 1.6054. Min Range: -1.6054

Max Act: 0.9137. Min Act: 0.0000

Data Index: 1108532 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 1.6054. Min Range: -1.6054

Max Act: 0.9055. Min Act: -0.0000

Data Index: 616391 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 1.6054. Min Range: -1.6054

Max Act: 0.9207. Min Act: 0.0000

Data Index: 29326 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 1.6054. Min Range: -1.6054

Max Act: 0.8678. Min Act: 0.0000

Data Index: 957192 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 1.6054. Min Range: -1.6054

Max Act: 0.8058. Min Act: -0.0000

Data Index: 1115912 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 1.6054. Min Range: -1.6054

Max Act: 0.8557. Min Act: -0.0000

Data Index: 152092 (C4 (Web Text))

Max Activating Token Index: 686