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

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

Neuron 2879 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3797. Min Act: -0.0000

Data Index: 1278221 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3554. Min Act: -0.0000

Data Index: 951567 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.4254. Min Act: -0.0000

Data Index: 1209520 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3728. Min Act: -0.0000

Data Index: 1650794 (Python Code)

Max Activating Token Index: 284

Text #4

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3595. Min Act: -0.0000

Data Index: 192379 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3653. Min Act: -0.0000

Data Index: 68818 (C4 (Web Text))

Max Activating Token Index: 791

Text #6

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3667. Min Act: -0.0000

Data Index: 68387 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3254. Min Act: -0.0000

Data Index: 917123 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3163. Min Act: -0.0000

Data Index: 906941 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3246. Min Act: -0.0000

Data Index: 1372883 (Python Code)

Max Activating Token Index: 437

Text #10

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3434. Min Act: -0.0000

Data Index: 1622432 (Python Code)

Max Activating Token Index: 866

Text #11

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3155. Min Act: -0.0000

Data Index: 573868 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3002. Min Act: -0.0000

Data Index: 1401744 (Python Code)

Max Activating Token Index: 233

Text #13

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3137. Min Act: -0.0000

Data Index: 637459 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3348. Min Act: -0.0000

Data Index: 505379 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3041. Min Act: -0.0000

Data Index: 48269 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3035. Min Act: -0.0000

Data Index: 8877 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3059. Min Act: -0.0000

Data Index: 432670 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3201. Min Act: -0.0000

Data Index: 1471302 (Python Code)

Max Activating Token Index: 74

Text #19

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2890. Min Act: -0.0000

Data Index: 733665 (C4 (Web Text))

Max Activating Token Index: 706