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

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

Neuron 3354 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0264. Min Range: -1.0264

Max Act: 1.0159. Min Act: -0.0000

Data Index: 226063 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.9548. Min Act: -0.0000

Data Index: 703757 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 1.0264. Min Range: -1.0264

Max Act: 1.0058. Min Act: -0.0000

Data Index: 1262264 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.9986. Min Act: -0.0000

Data Index: 497877 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 1.0264. Min Range: -1.0264

Max Act: 1.0264. Min Act: -0.0000

Data Index: 1353053 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.9127. Min Act: -0.0000

Data Index: 658566 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.8088. Min Act: -0.0000

Data Index: 718882 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.7956. Min Act: -0.0000

Data Index: 411320 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.7919. Min Act: -0.0000

Data Index: 866612 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.8367. Min Act: -0.0000

Data Index: 810174 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.8742. Min Act: -0.0000

Data Index: 1158094 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.8065. Min Act: -0.0000

Data Index: 1255754 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.7701. Min Act: -0.0000

Data Index: 1282888 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.8445. Min Act: -0.0000

Data Index: 444367 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.7997. Min Act: -0.0000

Data Index: 807170 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.8366. Min Act: -0.0000

Data Index: 331846 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.7820. Min Act: -0.0000

Data Index: 586980 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.7595. Min Act: -0.0000

Data Index: 212171 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.7979. Min Act: -0.0000

Data Index: 773692 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 1.0264. Min Range: -1.0264

Max Act: 0.7951. Min Act: -0.0000

Data Index: 895238 (C4 (Web Text))

Max Activating Token Index: 33