Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 77 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.1228. Min Range: -3.1228

Max Act: 3.1228. Min Act: -0.1700

Data Index: 654981 (C4 (Web Text))

Max Activating Token Index: 577

Text #1

Max Range: 3.1228. Min Range: -3.1228

Max Act: 3.0913. Min Act: -0.1700

Data Index: 994596 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 3.1228. Min Range: -3.1228

Max Act: 3.0597. Min Act: -0.1700

Data Index: 14890 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 3.1228. Min Range: -3.1228

Max Act: 3.0755. Min Act: -0.1700

Data Index: 1226307 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 3.1228. Min Range: -3.1228

Max Act: 3.0755. Min Act: -0.1700

Data Index: 154247 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 3.1228. Min Range: -3.1228

Max Act: 3.0439. Min Act: -0.1700

Data Index: 1335070 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 3.1228. Min Range: -3.1228

Max Act: 3.0755. Min Act: -0.1700

Data Index: 782365 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 3.1228. Min Range: -3.1228

Max Act: 3.0597. Min Act: -0.1700

Data Index: 279202 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 3.1228. Min Range: -3.1228

Max Act: 3.0439. Min Act: -0.1700

Data Index: 1220907 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 3.1228. Min Range: -3.1228

Max Act: 3.0439. Min Act: -0.1700

Data Index: 1033565 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 3.1228. Min Range: -3.1228

Max Act: 3.0439. Min Act: -0.1700

Data Index: 1168975 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 3.1228. Min Range: -3.1228

Max Act: 3.0439. Min Act: -0.1700

Data Index: 656297 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 3.1228. Min Range: -3.1228

Max Act: 3.0439. Min Act: -0.1700

Data Index: 108847 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 3.1228. Min Range: -3.1228

Max Act: 3.0282. Min Act: -0.1700

Data Index: 669587 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 3.1228. Min Range: -3.1228

Max Act: 3.0439. Min Act: -0.1700

Data Index: 77627 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 3.1228. Min Range: -3.1228

Max Act: 3.0282. Min Act: -0.1700

Data Index: 57831 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 3.1228. Min Range: -3.1228

Max Act: 3.0439. Min Act: -0.1700

Data Index: 178542 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 3.1228. Min Range: -3.1228

Max Act: 3.0439. Min Act: -0.1700

Data Index: 934267 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 3.1228. Min Range: -3.1228

Max Act: 3.0439. Min Act: -0.1700

Data Index: 718677 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 3.1228. Min Range: -3.1228

Max Act: 3.0282. Min Act: -0.1700

Data Index: 553676 (C4 (Web Text))

Max Activating Token Index: 726