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

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

Neuron 3277 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9792. Min Range: -2.9792

Max Act: 2.8226. Min Act: -0.0000

Data Index: 513560 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 2.9792. Min Range: -2.9792

Max Act: 2.9792. Min Act: -0.0000

Data Index: 1281259 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 2.9792. Min Range: -2.9792

Max Act: 2.4794. Min Act: -0.0000

Data Index: 350197 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 2.9792. Min Range: -2.9792

Max Act: 2.5789. Min Act: -0.0000

Data Index: 1226824 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 2.9792. Min Range: -2.9792

Max Act: 2.2573. Min Act: -0.0000

Data Index: 2586 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 2.9792. Min Range: -2.9792

Max Act: 2.2402. Min Act: -0.0000

Data Index: 462245 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 2.9792. Min Range: -2.9792

Max Act: 1.9648. Min Act: -0.0000

Data Index: 246831 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 2.9792. Min Range: -2.9792

Max Act: 2.4887. Min Act: -0.0000

Data Index: 906150 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 2.9792. Min Range: -2.9792

Max Act: 2.2214. Min Act: -0.0000

Data Index: 1132545 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 2.9792. Min Range: -2.9792

Max Act: 2.0840. Min Act: -0.0000

Data Index: 553169 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 2.9792. Min Range: -2.9792

Max Act: 2.0586. Min Act: -0.0000

Data Index: 1056686 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 2.9792. Min Range: -2.9792

Max Act: 2.2815. Min Act: -0.0000

Data Index: 1335542 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 2.9792. Min Range: -2.9792

Max Act: 1.9686. Min Act: -0.0000

Data Index: 277503 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 2.9792. Min Range: -2.9792

Max Act: 1.5851. Min Act: -0.0000

Data Index: 1268414 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 2.9792. Min Range: -2.9792

Max Act: 1.8141. Min Act: -0.0000

Data Index: 296957 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 2.9792. Min Range: -2.9792

Max Act: 1.8358. Min Act: -0.0000

Data Index: 738334 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 2.9792. Min Range: -2.9792

Max Act: 1.8009. Min Act: -0.0000

Data Index: 301523 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 2.9792. Min Range: -2.9792

Max Act: 1.9514. Min Act: -0.0000

Data Index: 120573 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 2.9792. Min Range: -2.9792

Max Act: 1.7476. Min Act: -0.0000

Data Index: 820310 (C4 (Web Text))

Max Activating Token Index: 295

Text #19

Max Range: 2.9792. Min Range: -2.9792

Max Act: 1.7303. Min Act: -0.0000

Data Index: 230130 (C4 (Web Text))

Max Activating Token Index: 579