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

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

Neuron 3622 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1166. Min Range: -1.1166

Max Act: 1.1166. Min Act: -0.0000

Data Index: 435647 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 1.1166. Min Range: -1.1166

Max Act: 1.0830. Min Act: -0.0000

Data Index: 1060357 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 1.1166. Min Range: -1.1166

Max Act: 1.0174. Min Act: -0.0000

Data Index: 614661 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 1.1166. Min Range: -1.1166

Max Act: 1.0576. Min Act: -0.0000

Data Index: 23879 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 1.1166. Min Range: -1.1166

Max Act: 0.9749. Min Act: -0.0000

Data Index: 1318839 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 1.1166. Min Range: -1.1166

Max Act: 0.8590. Min Act: -0.0000

Data Index: 1197970 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 1.1166. Min Range: -1.1166

Max Act: 0.8014. Min Act: -0.0000

Data Index: 181866 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 1.1166. Min Range: -1.1166

Max Act: 0.8128. Min Act: -0.0000

Data Index: 649777 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 1.1166. Min Range: -1.1166

Max Act: 0.7124. Min Act: -0.0000

Data Index: 747196 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 1.1166. Min Range: -1.1166

Max Act: 0.7628. Min Act: -0.0000

Data Index: 430360 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 1.1166. Min Range: -1.1166

Max Act: 0.7044. Min Act: -0.0000

Data Index: 705768 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 1.1166. Min Range: -1.1166

Max Act: 0.7604. Min Act: -0.0000

Data Index: 456803 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 1.1166. Min Range: -1.1166

Max Act: 0.6935. Min Act: -0.0000

Data Index: 1313206 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 1.1166. Min Range: -1.1166

Max Act: 0.6638. Min Act: -0.0000

Data Index: 173563 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 1.1166. Min Range: -1.1166

Max Act: 0.7179. Min Act: -0.0000

Data Index: 195007 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 1.1166. Min Range: -1.1166

Max Act: 0.7308. Min Act: -0.0000

Data Index: 679749 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 1.1166. Min Range: -1.1166

Max Act: 0.7166. Min Act: -0.0000

Data Index: 1044621 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 1.1166. Min Range: -1.1166

Max Act: 0.7084. Min Act: -0.0000

Data Index: 1282780 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 1.1166. Min Range: -1.1166

Max Act: 0.7636. Min Act: -0.0000

Data Index: 745893 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 1.1166. Min Range: -1.1166

Max Act: 0.6490. Min Act: -0.0000

Data Index: 335481 (C4 (Web Text))

Max Activating Token Index: 690