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

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

Neuron 5338 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2324. Min Range: -1.2324

Max Act: 1.2324. Min Act: -0.0000

Data Index: 924730 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.9770. Min Act: -0.0000

Data Index: 317881 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.8873. Min Act: -0.0000

Data Index: 368568 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.8132. Min Act: -0.0000

Data Index: 652988 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.8985. Min Act: -0.0000

Data Index: 745298 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.7954. Min Act: -0.0000

Data Index: 596157 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.7488. Min Act: -0.0000

Data Index: 1221224 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.8141. Min Act: -0.0000

Data Index: 740144 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.7268. Min Act: -0.0000

Data Index: 400078 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.6918. Min Act: -0.0000

Data Index: 202599 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.7688. Min Act: -0.0000

Data Index: 782587 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.6702. Min Act: -0.0000

Data Index: 746530 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.7338. Min Act: -0.0000

Data Index: 1053182 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.6543. Min Act: -0.0000

Data Index: 916807 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.6047. Min Act: -0.0000

Data Index: 954668 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.6634. Min Act: -0.0000

Data Index: 803982 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.6523. Min Act: -0.0000

Data Index: 420225 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.6676. Min Act: -0.0000

Data Index: 96640 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.6336. Min Act: -0.0000

Data Index: 488419 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.6324. Min Act: -0.0000

Data Index: 580828 (C4 (Web Text))

Max Activating Token Index: 44