Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1529 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.7355. Min Range: -5.7355

Max Act: 5.7355. Min Act: -0.1700

Data Index: 859753 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 5.7355. Min Range: -5.7355

Max Act: 5.6418. Min Act: -0.1700

Data Index: 1155229 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 5.7355. Min Range: -5.7355

Max Act: 5.5793. Min Act: -0.1700

Data Index: 1318578 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 5.7355. Min Range: -5.7355

Max Act: 5.5793. Min Act: -0.1700

Data Index: 956149 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 5.7355. Min Range: -5.7355

Max Act: 5.5480. Min Act: -0.1700

Data Index: 1214449 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 5.7355. Min Range: -5.7355

Max Act: 5.5168. Min Act: -0.1700

Data Index: 577485 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 5.7355. Min Range: -5.7355

Max Act: 5.5168. Min Act: -0.1700

Data Index: 822125 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 5.7355. Min Range: -5.7355

Max Act: 5.4543. Min Act: -0.1700

Data Index: 311006 (C4 (Web Text))

Max Activating Token Index: 408

Text #8

Max Range: 5.7355. Min Range: -5.7355

Max Act: 5.4543. Min Act: -0.1700

Data Index: 671925 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 5.7355. Min Range: -5.7355

Max Act: 5.4230. Min Act: -0.1700

Data Index: 1097561 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 5.7355. Min Range: -5.7355

Max Act: 5.3918. Min Act: -0.1700

Data Index: 869934 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 5.7355. Min Range: -5.7355

Max Act: 5.4543. Min Act: -0.1700

Data Index: 613554 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 5.7355. Min Range: -5.7355

Max Act: 5.4543. Min Act: -0.1700

Data Index: 354386 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 5.7355. Min Range: -5.7355

Max Act: 5.4543. Min Act: -0.1700

Data Index: 644936 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 5.7355. Min Range: -5.7355

Max Act: 5.3918. Min Act: -0.1700

Data Index: 1297691 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 5.7355. Min Range: -5.7355

Max Act: 5.4230. Min Act: -0.1700

Data Index: 185278 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 5.7355. Min Range: -5.7355

Max Act: 5.4230. Min Act: -0.1700

Data Index: 987660 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 5.7355. Min Range: -5.7355

Max Act: 5.3918. Min Act: -0.1700

Data Index: 821341 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 5.7355. Min Range: -5.7355

Max Act: 5.4230. Min Act: -0.1700

Data Index: 475457 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 5.7355. Min Range: -5.7355

Max Act: 5.3918. Min Act: -0.1700

Data Index: 623237 (C4 (Web Text))

Max Activating Token Index: 988