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

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

Neuron 3138 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.9792. Min Act: -0.0000

Data Index: 1319717 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.9887. Min Act: -0.0000

Data Index: 1206026 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.9336. Min Act: -0.0000

Data Index: 983511 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.9199. Min Act: -0.0000

Data Index: 534153 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.7788. Min Act: -0.0000

Data Index: 1217094 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.8361. Min Act: -0.0000

Data Index: 1035587 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.8326. Min Act: -0.0000

Data Index: 846233 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.7939. Min Act: -0.0000

Data Index: 649777 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.7896. Min Act: -0.0000

Data Index: 810534 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.7935. Min Act: -0.0000

Data Index: 962127 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.8271. Min Act: -0.0000

Data Index: 1033667 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.7198. Min Act: -0.0000

Data Index: 272 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.7787. Min Act: -0.0000

Data Index: 709575 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.7964. Min Act: -0.0000

Data Index: 297627 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.7463. Min Act: -0.0000

Data Index: 1471010 (Python Code)

Max Activating Token Index: 23

Text #15

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.7639. Min Act: -0.0000

Data Index: 1103387 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.7418. Min Act: -0.0000

Data Index: 313020 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.7597. Min Act: -0.0000

Data Index: 848026 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.6549. Min Act: -0.0000

Data Index: 1057338 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 0.9887. Min Range: -0.9887

Max Act: 0.7415. Min Act: -0.0000

Data Index: 1316041 (C4 (Web Text))

Max Activating Token Index: 307