Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2947 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.6805. Min Range: -3.6805

Max Act: 3.4698. Min Act: -0.0001

Data Index: 1275233 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 3.6805. Min Range: -3.6805

Max Act: 3.4541. Min Act: -0.0001

Data Index: 662094 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 3.6805. Min Range: -3.6805

Max Act: 3.2411. Min Act: -0.0001

Data Index: 379579 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 3.6805. Min Range: -3.6805

Max Act: 3.4055. Min Act: -0.0001

Data Index: 409064 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 3.6805. Min Range: -3.6805

Max Act: 3.3843. Min Act: -0.0001

Data Index: 130321 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 3.6805. Min Range: -3.6805

Max Act: 3.3846. Min Act: -0.0001

Data Index: 3629 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 3.6805. Min Range: -3.6805

Max Act: 2.6935. Min Act: -0.0001

Data Index: 907701 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 3.6805. Min Range: -3.6805

Max Act: 2.9984. Min Act: -0.0001

Data Index: 988244 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 3.6805. Min Range: -3.6805

Max Act: 3.1033. Min Act: -0.0001

Data Index: 225616 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 3.6805. Min Range: -3.6805

Max Act: 3.6805. Min Act: -0.0001

Data Index: 665329 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 3.6805. Min Range: -3.6805

Max Act: 2.9054. Min Act: -0.0001

Data Index: 478137 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 3.6805. Min Range: -3.6805

Max Act: 2.9012. Min Act: -0.0001

Data Index: 420080 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 3.6805. Min Range: -3.6805

Max Act: 2.8649. Min Act: -0.0001

Data Index: 1111213 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 3.6805. Min Range: -3.6805

Max Act: 3.1320. Min Act: -0.0001

Data Index: 1343311 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 3.6805. Min Range: -3.6805

Max Act: 3.1034. Min Act: -0.0001

Data Index: 187171 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 3.6805. Min Range: -3.6805

Max Act: 2.9605. Min Act: -0.0001

Data Index: 1354306 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 3.6805. Min Range: -3.6805

Max Act: 2.9556. Min Act: -0.0001

Data Index: 1129061 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 3.6805. Min Range: -3.6805

Max Act: 2.9275. Min Act: -0.0001

Data Index: 459587 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 3.6805. Min Range: -3.6805

Max Act: 2.7676. Min Act: -0.0001

Data Index: 673088 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 3.6805. Min Range: -3.6805

Max Act: 3.0154. Min Act: -0.0001

Data Index: 949058 (C4 (Web Text))

Max Activating Token Index: 797