Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2663 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2412. Min Act: -0.0003

Data Index: 458210 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2151. Min Act: -0.0003

Data Index: 684283 (C4 (Web Text))

Max Activating Token Index: 420

Text #2

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2430. Min Act: -0.0003

Data Index: 1247348 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2097. Min Act: -0.0003

Data Index: 920058 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2167. Min Act: -0.0003

Data Index: 1366187 (Python Code)

Max Activating Token Index: 248

Text #5

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1780. Min Act: -0.0003

Data Index: 164833 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1958. Min Act: -0.0003

Data Index: 1169329 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1965. Min Act: -0.0003

Data Index: 1007578 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2028. Min Act: -0.0003

Data Index: 1115462 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2028. Min Act: -0.0003

Data Index: 741853 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2022. Min Act: -0.0003

Data Index: 1103572 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2079. Min Act: -0.0003

Data Index: 387801 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1929. Min Act: -0.0003

Data Index: 1303217 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1920. Min Act: -0.0003

Data Index: 457452 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1974. Min Act: -0.0003

Data Index: 626483 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2050. Min Act: -0.0003

Data Index: 835004 (C4 (Web Text))

Max Activating Token Index: 478

Text #16

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1915. Min Act: -0.0003

Data Index: 249253 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.2053. Min Act: -0.0003

Data Index: 1195823 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1907. Min Act: -0.0003

Data Index: 373851 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 0.2430. Min Range: -0.2430

Max Act: 0.1893. Min Act: -0.0003

Data Index: 646328 (C4 (Web Text))

Max Activating Token Index: 229