Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2385 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.7224. Min Act: -0.0002

Data Index: 590573 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.7005. Min Act: -0.0001

Data Index: 767843 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.7222. Min Act: -0.0001

Data Index: 1120491 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.6047. Min Act: -0.0001

Data Index: 653469 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.6752. Min Act: -0.0002

Data Index: 1241130 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.6526. Min Act: -0.0002

Data Index: 1136210 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.6039. Min Act: -0.0001

Data Index: 602493 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.6151. Min Act: -0.0001

Data Index: 1205875 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.5778. Min Act: -0.0002

Data Index: 1322485 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.6153. Min Act: -0.0002

Data Index: 540266 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.6000. Min Act: -0.0002

Data Index: 266464 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.6293. Min Act: -0.0001

Data Index: 205977 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.6340. Min Act: -0.0001

Data Index: 931782 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.5799. Min Act: -0.0001

Data Index: 1040102 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.5685. Min Act: -0.0001

Data Index: 1239146 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.6506. Min Act: -0.0002

Data Index: 54848 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.5607. Min Act: -0.0001

Data Index: 980414 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.6030. Min Act: -0.0001

Data Index: 866807 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.6036. Min Act: -0.0001

Data Index: 676256 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 0.7224. Min Range: -0.7224

Max Act: 0.6185. Min Act: -0.0001

Data Index: 842710 (C4 (Web Text))

Max Activating Token Index: 771