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

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

Neuron 2040 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2165. Min Range: -1.2165

Max Act: 1.2165. Min Act: -0.0000

Data Index: 1007366 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 1.2165. Min Range: -1.2165

Max Act: 1.0165. Min Act: -0.0000

Data Index: 1307118 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.9116. Min Act: -0.0000

Data Index: 609748 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.9494. Min Act: -0.0000

Data Index: 149439 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.9478. Min Act: -0.0000

Data Index: 197721 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.9123. Min Act: -0.0000

Data Index: 993757 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.8644. Min Act: -0.0000

Data Index: 951572 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.8678. Min Act: -0.0000

Data Index: 552812 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.8533. Min Act: -0.0000

Data Index: 630674 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.8359. Min Act: -0.0000

Data Index: 427085 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.8925. Min Act: -0.0000

Data Index: 1239397 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.8893. Min Act: -0.0000

Data Index: 712349 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.9310. Min Act: -0.0000

Data Index: 1148936 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.8288. Min Act: -0.0000

Data Index: 1219245 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.7774. Min Act: -0.0000

Data Index: 1003626 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.8129. Min Act: -0.0000

Data Index: 3408 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.8900. Min Act: -0.0000

Data Index: 65189 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.8588. Min Act: -0.0000

Data Index: 19156 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.7767. Min Act: -0.0000

Data Index: 687821 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 1.2165. Min Range: -1.2165

Max Act: 0.8251. Min Act: -0.0000

Data Index: 746747 (C4 (Web Text))

Max Activating Token Index: 744