Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1594 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2189. Min Act: -0.0002

Data Index: 1234505 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2459. Min Act: -0.0002

Data Index: 828329 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2406. Min Act: -0.0002

Data Index: 1045869 (C4 (Web Text))

Max Activating Token Index: 593

Text #3

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2457. Min Act: -0.0002

Data Index: 1085033 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2190. Min Act: -0.0002

Data Index: 463100 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2129. Min Act: -0.0002

Data Index: 1262735 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2165. Min Act: -0.0002

Data Index: 447085 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2136. Min Act: -0.0002

Data Index: 139359 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2070. Min Act: -0.0002

Data Index: 444789 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2121. Min Act: -0.0002

Data Index: 724534 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2105. Min Act: -0.0002

Data Index: 987795 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2013. Min Act: -0.0002

Data Index: 823131 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2040. Min Act: -0.0002

Data Index: 1204156 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1942. Min Act: -0.0002

Data Index: 465317 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1991. Min Act: -0.0002

Data Index: 148277 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1980. Min Act: -0.0002

Data Index: 1063947 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2049. Min Act: -0.0002

Data Index: 1247587 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2032. Min Act: -0.0002

Data Index: 299880 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1950. Min Act: -0.0002

Data Index: 739818 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1944. Min Act: -0.0002

Data Index: 36637 (C4 (Web Text))

Max Activating Token Index: 453