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

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

Neuron 3898 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8090. Min Range: -1.8090

Max Act: 1.8090. Min Act: -0.0000

Data Index: 779132 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 1.8090. Min Range: -1.8090

Max Act: 1.6009. Min Act: -0.0000

Data Index: 183623 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 1.8090. Min Range: -1.8090

Max Act: 1.3399. Min Act: -0.0000

Data Index: 235339 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 1.8090. Min Range: -1.8090

Max Act: 1.3185. Min Act: -0.0000

Data Index: 1243725 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 1.8090. Min Range: -1.8090

Max Act: 1.2246. Min Act: -0.0000

Data Index: 771248 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 1.8090. Min Range: -1.8090

Max Act: 1.0905. Min Act: -0.0000

Data Index: 779031 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 1.8090. Min Range: -1.8090

Max Act: 1.0667. Min Act: -0.0000

Data Index: 470830 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 1.8090. Min Range: -1.8090

Max Act: 1.0451. Min Act: -0.0000

Data Index: 50942 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 1.8090. Min Range: -1.8090

Max Act: 0.9595. Min Act: -0.0000

Data Index: 727058 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 1.8090. Min Range: -1.8090

Max Act: 0.9359. Min Act: -0.0000

Data Index: 268554 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 1.8090. Min Range: -1.8090

Max Act: 0.8876. Min Act: -0.0000

Data Index: 1279428 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 1.8090. Min Range: -1.8090

Max Act: 0.9345. Min Act: -0.0000

Data Index: 520160 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 1.8090. Min Range: -1.8090

Max Act: 0.9337. Min Act: -0.0000

Data Index: 803065 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 1.8090. Min Range: -1.8090

Max Act: 0.9370. Min Act: -0.0000

Data Index: 1180482 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 1.8090. Min Range: -1.8090

Max Act: 0.8710. Min Act: -0.0000

Data Index: 315750 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 1.8090. Min Range: -1.8090

Max Act: 0.9212. Min Act: -0.0000

Data Index: 900243 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 1.8090. Min Range: -1.8090

Max Act: 0.8776. Min Act: -0.0000

Data Index: 483057 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 1.8090. Min Range: -1.8090

Max Act: 0.9069. Min Act: -0.0000

Data Index: 1164604 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 1.8090. Min Range: -1.8090

Max Act: 0.9379. Min Act: -0.0000

Data Index: 1034017 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 1.8090. Min Range: -1.8090

Max Act: 0.9080. Min Act: -0.0000

Data Index: 266328 (C4 (Web Text))

Max Activating Token Index: 270