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

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

Neuron 5094 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.7162. Min Act: -0.0000

Data Index: 605257 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.7264. Min Act: -0.0000

Data Index: 402021 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.6990. Min Act: 0.0000

Data Index: 1236689 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1200833 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.6677. Min Act: -0.0000

Data Index: 1258383 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.6811. Min Act: -0.0000

Data Index: 641799 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.6400. Min Act: -0.0000

Data Index: 475004 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.6341. Min Act: -0.0000

Data Index: 1347795 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.6041. Min Act: -0.0000

Data Index: 576936 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.6360. Min Act: -0.0000

Data Index: 163828 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.6259. Min Act: -0.0000

Data Index: 1347111 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.6077. Min Act: -0.0000

Data Index: 380648 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.5873. Min Act: -0.0000

Data Index: 1205782 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.5974. Min Act: -0.0000

Data Index: 944256 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.5945. Min Act: 0.0000

Data Index: 1186319 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.5944. Min Act: -0.0000

Data Index: 797952 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.5581. Min Act: -0.0000

Data Index: 226386 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.5864. Min Act: -0.0000

Data Index: 193729 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.5465. Min Act: 0.0001

Data Index: 1047830 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.5612. Min Act: -0.0000

Data Index: 154377 (C4 (Web Text))

Max Activating Token Index: 447