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

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

Neuron 1265 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1931. Min Act: -0.0000

Data Index: 467408 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1578. Min Act: -0.0000

Data Index: 794603 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1508. Min Act: -0.0000

Data Index: 998521 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1492. Min Act: -0.0000

Data Index: 968236 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1286. Min Act: -0.0000

Data Index: 998247 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1189. Min Act: -0.0000

Data Index: 214044 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1182. Min Act: -0.0000

Data Index: 973128 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1187. Min Act: -0.0000

Data Index: 1316782 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1187. Min Act: -0.0000

Data Index: 867043 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1106. Min Act: -0.0000

Data Index: 633756 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.0964. Min Act: -0.0000

Data Index: 1000910 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1027. Min Act: -0.0000

Data Index: 1319297 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.0999. Min Act: -0.0000

Data Index: 1047052 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.0931. Min Act: -0.0000

Data Index: 452230 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.0853. Min Act: -0.0000

Data Index: 278974 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.0913. Min Act: -0.0000

Data Index: 197349 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.0908. Min Act: -0.0000

Data Index: 1303583 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.0857. Min Act: -0.0000

Data Index: 908881 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.0858. Min Act: -0.0000

Data Index: 1133515 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.0873. Min Act: -0.0000

Data Index: 217449 (C4 (Web Text))

Max Activating Token Index: 897