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

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

Neuron 622 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2364. Min Act: -0.0001

Data Index: 549489 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2353. Min Act: -0.0001

Data Index: 662553 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2093. Min Act: -0.0001

Data Index: 665800 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2154. Min Act: -0.0001

Data Index: 148829 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1904. Min Act: -0.0001

Data Index: 1019235 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2014. Min Act: -0.0001

Data Index: 280766 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2097. Min Act: -0.0001

Data Index: 968868 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2015. Min Act: -0.0001

Data Index: 1488828 (Python Code)

Max Activating Token Index: 7

Text #8

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1992. Min Act: -0.0001

Data Index: 347438 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.2094. Min Act: -0.0001

Data Index: 378436 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1972. Min Act: -0.0001

Data Index: 1224127 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1958. Min Act: -0.0001

Data Index: 330447 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1881. Min Act: -0.0001

Data Index: 1173798 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1808. Min Act: -0.0001

Data Index: 931279 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1859. Min Act: -0.0001

Data Index: 537815 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1900. Min Act: -0.0001

Data Index: 1043177 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1893. Min Act: -0.0001

Data Index: 26057 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1908. Min Act: -0.0001

Data Index: 79465 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1842. Min Act: -0.0001

Data Index: 1285951 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 0.2364. Min Range: -0.2364

Max Act: 0.1875. Min Act: -0.0001

Data Index: 577950 (C4 (Web Text))

Max Activating Token Index: 728