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

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

Neuron 647 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.5433. Min Act: -0.0000

Data Index: 423626 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4905. Min Act: -0.0000

Data Index: 415656 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4259. Min Act: -0.0000

Data Index: 757944 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.3814. Min Act: -0.0000

Data Index: 920642 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4187. Min Act: -0.0000

Data Index: 556291 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4155. Min Act: -0.0000

Data Index: 474444 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.3724. Min Act: -0.0000

Data Index: 16799 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.4232. Min Act: -0.0000

Data Index: 1239636 (C4 (Web Text))

Max Activating Token Index: 878

Text #8

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.2956. Min Act: -0.0000

Data Index: 144439 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.3051. Min Act: -0.0000

Data Index: 1352061 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.2805. Min Act: -0.0000

Data Index: 31962 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.2677. Min Act: -0.0000

Data Index: 658664 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.2222. Min Act: -0.0000

Data Index: 1332361 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.2859. Min Act: -0.0000

Data Index: 1357584 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.2791. Min Act: -0.0000

Data Index: 1650134 (Python Code)

Max Activating Token Index: 209

Text #15

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.2562. Min Act: -0.0000

Data Index: 142178 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.2574. Min Act: -0.0000

Data Index: 1009715 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.2532. Min Act: -0.0000

Data Index: 369518 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.2473. Min Act: -0.0000

Data Index: 286604 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 0.5433. Min Range: -0.5433

Max Act: 0.2568. Min Act: -0.0000

Data Index: 160786 (C4 (Web Text))

Max Activating Token Index: 734