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

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

Neuron 4201 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: 0.3057. Min Range: -0.3057

Max Act: 0.3057. Min Act: -0.0000

Data Index: 1157121 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.3048. Min Act: -0.0000

Data Index: 1232294 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2597. Min Act: -0.0000

Data Index: 128569 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2815. Min Act: -0.0000

Data Index: 1030441 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2650. Min Act: -0.0000

Data Index: 109130 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2626. Min Act: -0.0000

Data Index: 324568 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2616. Min Act: -0.0000

Data Index: 1154907 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2609. Min Act: -0.0000

Data Index: 785904 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2511. Min Act: -0.0000

Data Index: 263172 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2505. Min Act: -0.0000

Data Index: 338965 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2506. Min Act: -0.0000

Data Index: 1142206 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2374. Min Act: -0.0000

Data Index: 1240051 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2417. Min Act: -0.0000

Data Index: 968126 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2422. Min Act: -0.0000

Data Index: 173662 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2375. Min Act: -0.0000

Data Index: 886734 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2293. Min Act: -0.0000

Data Index: 905195 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2293. Min Act: -0.0000

Data Index: 367712 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2273. Min Act: -0.0000

Data Index: 1164485 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2117. Min Act: -0.0000

Data Index: 735708 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 0.3057. Min Range: -0.3057

Max Act: 0.2240. Min Act: -0.0000

Data Index: 284369 (C4 (Web Text))

Max Activating Token Index: 466