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

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

Neuron 3264 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: 0.2570. Min Range: -0.2570

Max Act: 0.2245. Min Act: -0.0000

Data Index: 570732 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.2570. Min Act: -0.0000

Data Index: 459984 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.2404. Min Act: -0.0000

Data Index: 1074403 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.2270. Min Act: -0.0000

Data Index: 398405 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.2171. Min Act: -0.0000

Data Index: 1025643 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.2022. Min Act: -0.0000

Data Index: 1043394 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1878. Min Act: -0.0000

Data Index: 337944 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.2066. Min Act: -0.0000

Data Index: 1337522 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.2191. Min Act: -0.0000

Data Index: 287645 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.2325. Min Act: -0.0000

Data Index: 1280054 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.2068. Min Act: -0.0000

Data Index: 255979 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1987. Min Act: -0.0000

Data Index: 928152 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1963. Min Act: -0.0000

Data Index: 514594 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1932. Min Act: -0.0000

Data Index: 315611 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.2005. Min Act: -0.0000

Data Index: 350478 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.2192. Min Act: -0.0000

Data Index: 823922 (C4 (Web Text))

Max Activating Token Index: 404

Text #16

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1934. Min Act: -0.0000

Data Index: 681671 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1982. Min Act: -0.0000

Data Index: 549647 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.2040. Min Act: -0.0000

Data Index: 218813 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 0.2570. Min Range: -0.2570

Max Act: 0.1918. Min Act: -0.0000

Data Index: 851850 (C4 (Web Text))

Max Activating Token Index: 624