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

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

Neuron 5034 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3189. Min Range: -1.3189

Max Act: 1.0992. Min Act: -0.0000

Data Index: 960199 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 1.3189. Min Range: -1.3189

Max Act: 1.3189. Min Act: -0.0000

Data Index: 827878 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 1.3189. Min Range: -1.3189

Max Act: 1.0516. Min Act: -0.0000

Data Index: 494872 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 1.3189. Min Range: -1.3189

Max Act: 0.9804. Min Act: -0.0000

Data Index: 725759 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 1.3189. Min Range: -1.3189

Max Act: 0.9470. Min Act: -0.0000

Data Index: 60303 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 1.3189. Min Range: -1.3189

Max Act: 0.8553. Min Act: -0.0000

Data Index: 1032304 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 1.3189. Min Range: -1.3189

Max Act: 0.9520. Min Act: -0.0000

Data Index: 626022 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 1.3189. Min Range: -1.3189

Max Act: 0.8589. Min Act: -0.0000

Data Index: 508454 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 1.3189. Min Range: -1.3189

Max Act: 0.8872. Min Act: -0.0000

Data Index: 589853 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 1.3189. Min Range: -1.3189

Max Act: 0.8545. Min Act: -0.0000

Data Index: 22318 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 1.3189. Min Range: -1.3189

Max Act: 0.8499. Min Act: -0.0000

Data Index: 893456 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 1.3189. Min Range: -1.3189

Max Act: 0.8453. Min Act: -0.0000

Data Index: 1262628 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 1.3189. Min Range: -1.3189

Max Act: 0.7860. Min Act: -0.0000

Data Index: 893442 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 1.3189. Min Range: -1.3189

Max Act: 0.8170. Min Act: -0.0000

Data Index: 1001610 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 1.3189. Min Range: -1.3189

Max Act: 0.7096. Min Act: -0.0000

Data Index: 981975 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 1.3189. Min Range: -1.3189

Max Act: 0.8203. Min Act: -0.0000

Data Index: 961043 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 1.3189. Min Range: -1.3189

Max Act: 0.8970. Min Act: -0.0001

Data Index: 517389 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 1.3189. Min Range: -1.3189

Max Act: 0.7900. Min Act: -0.0000

Data Index: 187208 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 1.3189. Min Range: -1.3189

Max Act: 0.7728. Min Act: -0.0000

Data Index: 1129817 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 1.3189. Min Range: -1.3189

Max Act: 0.8118. Min Act: -0.0000

Data Index: 772205 (C4 (Web Text))

Max Activating Token Index: 76