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

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

Neuron 2311 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.4636. Min Act: -0.0001

Data Index: 1181963 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.6328. Min Act: -0.0001

Data Index: 1135280 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.5742. Min Act: -0.0001

Data Index: 148579 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.4814. Min Act: -0.0001

Data Index: 422284 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.6555. Min Act: -0.0001

Data Index: 1027170 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.5592. Min Act: -0.0001

Data Index: 779750 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.3800. Min Act: -0.0001

Data Index: 1065854 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.3773. Min Act: -0.0001

Data Index: 164083 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.4620. Min Act: -0.0001

Data Index: 886641 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.3658. Min Act: -0.0001

Data Index: 1001075 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.2606. Min Act: -0.0001

Data Index: 618204 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.3481. Min Act: -0.0001

Data Index: 920574 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.3511. Min Act: -0.0001

Data Index: 1061994 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.3046. Min Act: -0.0001

Data Index: 392016 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.2924. Min Act: -0.0001

Data Index: 774486 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.2112. Min Act: -0.0001

Data Index: 332746 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.1820. Min Act: -0.0001

Data Index: 965745 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.2283. Min Act: -0.0001

Data Index: 322149 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.1687. Min Act: -0.0001

Data Index: 367268 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.1532. Min Act: -0.0001

Data Index: 633292 (C4 (Web Text))

Max Activating Token Index: 645