Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1862 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.6301. Min Range: -5.6301

Max Act: 5.6301. Min Act: -0.1700

Data Index: 381782 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 5.6301. Min Range: -5.6301

Max Act: 5.2863. Min Act: -0.1700

Data Index: 912417 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 5.6301. Min Range: -5.6301

Max Act: 5.3488. Min Act: -0.1700

Data Index: 1227050 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 5.6301. Min Range: -5.6301

Max Act: 5.2551. Min Act: -0.1700

Data Index: 225846 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 5.6301. Min Range: -5.6301

Max Act: 5.2551. Min Act: -0.1700

Data Index: 53536 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 5.6301. Min Range: -5.6301

Max Act: 5.2238. Min Act: -0.1700

Data Index: 265919 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 5.6301. Min Range: -5.6301

Max Act: 5.1926. Min Act: -0.1700

Data Index: 31976 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 5.6301. Min Range: -5.6301

Max Act: 5.1301. Min Act: -0.1700

Data Index: 641845 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 5.6301. Min Range: -5.6301

Max Act: 5.1926. Min Act: -0.1700

Data Index: 1208297 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 5.6301. Min Range: -5.6301

Max Act: 5.1613. Min Act: -0.1700

Data Index: 587296 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 5.6301. Min Range: -5.6301

Max Act: 5.1613. Min Act: -0.1700

Data Index: 1343552 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 5.6301. Min Range: -5.6301

Max Act: 5.1301. Min Act: -0.1700

Data Index: 45639 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 5.6301. Min Range: -5.6301

Max Act: 5.1301. Min Act: -0.1700

Data Index: 1007564 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 5.6301. Min Range: -5.6301

Max Act: 5.1301. Min Act: -0.1700

Data Index: 40671 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 5.6301. Min Range: -5.6301

Max Act: 5.1301. Min Act: -0.1700

Data Index: 725943 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 5.6301. Min Range: -5.6301

Max Act: 5.0988. Min Act: -0.1700

Data Index: 435232 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 5.6301. Min Range: -5.6301

Max Act: 5.0988. Min Act: -0.1700

Data Index: 174514 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 5.6301. Min Range: -5.6301

Max Act: 5.0988. Min Act: -0.1700

Data Index: 707575 (C4 (Web Text))

Max Activating Token Index: 468

Text #18

Max Range: 5.6301. Min Range: -5.6301

Max Act: 5.0988. Min Act: -0.1700

Data Index: 799370 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 5.6301. Min Range: -5.6301

Max Act: 5.1613. Min Act: -0.1700

Data Index: 309476 (C4 (Web Text))

Max Activating Token Index: 466