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

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

Neuron 1575 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7376. Min Range: -3.7376

Max Act: 3.7376. Min Act: -0.1700

Data Index: 86688 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 3.7376. Min Range: -3.7376

Max Act: 3.7376. Min Act: -0.1700

Data Index: 451057 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 3.7376. Min Range: -3.7376

Max Act: 3.7063. Min Act: -0.1700

Data Index: 494899 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 3.7376. Min Range: -3.7376

Max Act: 3.6437. Min Act: -0.1700

Data Index: 675052 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 3.7376. Min Range: -3.7376

Max Act: 3.6437. Min Act: -0.1700

Data Index: 217197 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 3.7376. Min Range: -3.7376

Max Act: 3.5811. Min Act: -0.1700

Data Index: 839322 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 3.7376. Min Range: -3.7376

Max Act: 3.5811. Min Act: -0.1700

Data Index: 376576 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 3.7376. Min Range: -3.7376

Max Act: 3.5498. Min Act: -0.1700

Data Index: 546450 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 3.7376. Min Range: -3.7376

Max Act: 3.5498. Min Act: -0.1700

Data Index: 311968 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 3.7376. Min Range: -3.7376

Max Act: 3.5498. Min Act: -0.1700

Data Index: 33941 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 3.7376. Min Range: -3.7376

Max Act: 3.5811. Min Act: -0.1700

Data Index: 29565 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 3.7376. Min Range: -3.7376

Max Act: 3.5185. Min Act: -0.1700

Data Index: 687187 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 3.7376. Min Range: -3.7376

Max Act: 3.4871. Min Act: -0.1700

Data Index: 245719 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 3.7376. Min Range: -3.7376

Max Act: 3.4871. Min Act: -0.1700

Data Index: 697002 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 3.7376. Min Range: -3.7376

Max Act: 3.4871. Min Act: -0.1700

Data Index: 404945 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 3.7376. Min Range: -3.7376

Max Act: 3.4871. Min Act: -0.1700

Data Index: 671443 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 3.7376. Min Range: -3.7376

Max Act: 3.4871. Min Act: -0.1700

Data Index: 977597 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 3.7376. Min Range: -3.7376

Max Act: 3.4871. Min Act: -0.1700

Data Index: 486003 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 3.7376. Min Range: -3.7376

Max Act: 3.4871. Min Act: -0.1700

Data Index: 302903 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 3.7376. Min Range: -3.7376

Max Act: 3.4558. Min Act: -0.1700

Data Index: 543444 (C4 (Web Text))

Max Activating Token Index: 876