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

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

Neuron 5978 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5159. Min Range: -5.5159

Max Act: 5.5159. Min Act: -0.0000

Data Index: 393312 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 5.5159. Min Range: -5.5159

Max Act: 5.4881. Min Act: -0.0000

Data Index: 194854 (C4 (Web Text))

Max Activating Token Index: 334

Text #2

Max Range: 5.5159. Min Range: -5.5159

Max Act: 5.1931. Min Act: -0.0000

Data Index: 1242582 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 5.5159. Min Range: -5.5159

Max Act: 4.3201. Min Act: -0.0000

Data Index: 863895 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 5.5159. Min Range: -5.5159

Max Act: 4.3299. Min Act: -0.0000

Data Index: 1593195 (Python Code)

Max Activating Token Index: 977

Text #5

Max Range: 5.5159. Min Range: -5.5159

Max Act: 3.9178. Min Act: -0.0000

Data Index: 497067 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 5.5159. Min Range: -5.5159

Max Act: 3.7833. Min Act: -0.0000

Data Index: 79321 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 5.5159. Min Range: -5.5159

Max Act: 3.9255. Min Act: -0.0000

Data Index: 50237 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 5.5159. Min Range: -5.5159

Max Act: 3.7817. Min Act: -0.0000

Data Index: 695530 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 5.5159. Min Range: -5.5159

Max Act: 3.4506. Min Act: -0.0000

Data Index: 1479808 (Python Code)

Max Activating Token Index: 189

Text #10

Max Range: 5.5159. Min Range: -5.5159

Max Act: 3.4276. Min Act: -0.0000

Data Index: 696414 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 5.5159. Min Range: -5.5159

Max Act: 3.0999. Min Act: -0.0000

Data Index: 889672 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 5.5159. Min Range: -5.5159

Max Act: 3.2028. Min Act: -0.0000

Data Index: 702565 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 5.5159. Min Range: -5.5159

Max Act: 3.1206. Min Act: -0.0000

Data Index: 1079079 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 5.5159. Min Range: -5.5159

Max Act: 3.0907. Min Act: -0.0000

Data Index: 1421315 (Python Code)

Max Activating Token Index: 509

Text #15

Max Range: 5.5159. Min Range: -5.5159

Max Act: 3.1009. Min Act: 0.0000

Data Index: 1383873 (Python Code)

Max Activating Token Index: 177

Text #16

Max Range: 5.5159. Min Range: -5.5159

Max Act: 3.0331. Min Act: -0.0000

Data Index: 1562079 (Python Code)

Max Activating Token Index: 240

Text #17

Max Range: 5.5159. Min Range: -5.5159

Max Act: 3.0156. Min Act: -0.0000

Data Index: 815510 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 5.5159. Min Range: -5.5159

Max Act: 2.9841. Min Act: -0.0000

Data Index: 270870 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 5.5159. Min Range: -5.5159

Max Act: 2.8207. Min Act: -0.0000

Data Index: 644142 (C4 (Web Text))

Max Activating Token Index: 217