Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2648 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0054. Min Act: -0.0002

Data Index: 777353 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0055. Min Act: -0.0002

Data Index: 37279 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0054. Min Act: -0.0002

Data Index: 162685 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0054. Min Act: -0.0002

Data Index: 677585 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0053. Min Act: -0.0002

Data Index: 713352 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0053. Min Act: -0.0002

Data Index: 1270436 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0053. Min Act: -0.0002

Data Index: 684576 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0053. Min Act: -0.0002

Data Index: 823640 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0052. Min Act: -0.0002

Data Index: 1211195 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0052. Min Act: -0.0002

Data Index: 1291680 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0052. Min Act: -0.0002

Data Index: 1108664 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0052. Min Act: -0.0002

Data Index: 1317566 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0052. Min Act: -0.0002

Data Index: 73244 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0052. Min Act: -0.0002

Data Index: 705923 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0052. Min Act: -0.0002

Data Index: 997468 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0052. Min Act: -0.0002

Data Index: 767876 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0052. Min Act: -0.0002

Data Index: 544463 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0051. Min Act: -0.0002

Data Index: 422689 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0052. Min Act: -0.0002

Data Index: 1188411 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0051. Min Act: -0.0002

Data Index: 157306 (C4 (Web Text))

Max Activating Token Index: 705