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

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

Neuron 1248 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.7030. Min Act: -0.0001

Data Index: 865672 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.6498. Min Act: -0.0001

Data Index: 147334 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.7338. Min Act: -0.0002

Data Index: 519560 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.6941. Min Act: -0.0002

Data Index: 596972 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.6651. Min Act: -0.0002

Data Index: 187058 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.6550. Min Act: -0.0002

Data Index: 972415 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.6433. Min Act: -0.0002

Data Index: 795160 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.6528. Min Act: -0.0002

Data Index: 417091 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.6465. Min Act: -0.0002

Data Index: 929163 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.6072. Min Act: -0.0002

Data Index: 534656 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.5953. Min Act: -0.0001

Data Index: 1069477 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.6243. Min Act: -0.0002

Data Index: 205405 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.6394. Min Act: -0.0001

Data Index: 236361 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.6358. Min Act: -0.0002

Data Index: 605906 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.6214. Min Act: -0.0002

Data Index: 184598 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.5973. Min Act: -0.0001

Data Index: 1091085 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.6308. Min Act: -0.0002

Data Index: 475636 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.5967. Min Act: -0.0002

Data Index: 990785 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.6497. Min Act: -0.0001

Data Index: 632375 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 0.7338. Min Range: -0.7338

Max Act: 0.5592. Min Act: -0.0001

Data Index: 407663 (C4 (Web Text))

Max Activating Token Index: 979