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

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

Neuron 2044 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7725. Min Range: -3.7725

Max Act: 3.7725. Min Act: -0.1700

Data Index: 137334 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 3.7725. Min Range: -3.7725

Max Act: 3.7725. Min Act: -0.1700

Data Index: 1280594 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.7725. Min Range: -3.7725

Max Act: 3.7725. Min Act: -0.1700

Data Index: 1247264 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.7725. Min Range: -3.7725

Max Act: 3.6786. Min Act: -0.1700

Data Index: 1251284 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 3.7725. Min Range: -3.7725

Max Act: 3.6160. Min Act: -0.1700

Data Index: 1232125 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 3.7725. Min Range: -3.7725

Max Act: 3.5534. Min Act: -0.1700

Data Index: 131361 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 3.7725. Min Range: -3.7725

Max Act: 3.5220. Min Act: -0.1700

Data Index: 867886 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 3.7725. Min Range: -3.7725

Max Act: 3.4593. Min Act: -0.1700

Data Index: 930810 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 3.7725. Min Range: -3.7725

Max Act: 3.4593. Min Act: -0.1700

Data Index: 395484 (C4 (Web Text))

Max Activating Token Index: 670

Text #9

Max Range: 3.7725. Min Range: -3.7725

Max Act: 3.3966. Min Act: -0.1700

Data Index: 62515 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 3.7725. Min Range: -3.7725

Max Act: 3.4593. Min Act: -0.1700

Data Index: 978517 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 3.7725. Min Range: -3.7725

Max Act: 3.4593. Min Act: -0.1700

Data Index: 1324006 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 3.7725. Min Range: -3.7725

Max Act: 3.4280. Min Act: -0.1700

Data Index: 571473 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 3.7725. Min Range: -3.7725

Max Act: 3.4280. Min Act: -0.1700

Data Index: 534428 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 3.7725. Min Range: -3.7725

Max Act: 3.3966. Min Act: -0.1700

Data Index: 517112 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 3.7725. Min Range: -3.7725

Max Act: 3.4280. Min Act: -0.1700

Data Index: 194077 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 3.7725. Min Range: -3.7725

Max Act: 3.4280. Min Act: -0.1700

Data Index: 854194 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 3.7725. Min Range: -3.7725

Max Act: 3.3966. Min Act: -0.1700

Data Index: 405389 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 3.7725. Min Range: -3.7725

Max Act: 3.4280. Min Act: -0.1700

Data Index: 281934 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 3.7725. Min Range: -3.7725

Max Act: 3.4280. Min Act: -0.1700

Data Index: 738151 (C4 (Web Text))

Max Activating Token Index: 575