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

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

Neuron 2187 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0555. Min Act: -0.0001

Data Index: 698181 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0488. Min Act: -0.0001

Data Index: 600144 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0322. Min Act: -0.0001

Data Index: 1024504 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0326. Min Act: -0.0001

Data Index: 1164274 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0310. Min Act: -0.0001

Data Index: 1414755 (Python Code)

Max Activating Token Index: 472

Text #5

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0312. Min Act: -0.0001

Data Index: 909635 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0297. Min Act: -0.0001

Data Index: 346389 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0280. Min Act: -0.0001

Data Index: 1011492 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0282. Min Act: -0.0001

Data Index: 1549101 (Python Code)

Max Activating Token Index: 1014

Text #9

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0285. Min Act: -0.0001

Data Index: 552957 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0297. Min Act: -0.0001

Data Index: 224202 (C4 (Web Text))

Max Activating Token Index: 259

Text #11

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0280. Min Act: -0.0001

Data Index: 413599 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0283. Min Act: -0.0001

Data Index: 450863 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0286. Min Act: -0.0001

Data Index: 237269 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0278. Min Act: -0.0001

Data Index: 707739 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0265. Min Act: -0.0001

Data Index: 1381125 (Python Code)

Max Activating Token Index: 929

Text #16

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0277. Min Act: -0.0001

Data Index: 1184445 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0269. Min Act: -0.0001

Data Index: 1302797 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0254. Min Act: -0.0001

Data Index: 947226 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 0.0555. Min Range: -0.0555

Max Act: 0.0263. Min Act: -0.0001

Data Index: 1255010 (C4 (Web Text))

Max Activating Token Index: 813