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

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

Neuron 469 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: 3.5823. Min Range: -3.5823

Max Act: 3.5823. Min Act: -0.1700

Data Index: 635530 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.4569. Min Act: -0.1700

Data Index: 1037653 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.3471. Min Act: -0.1700

Data Index: 1351551 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.3471. Min Act: -0.1700

Data Index: 1322501 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.3157. Min Act: -0.1700

Data Index: 656591 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.3314. Min Act: -0.1700

Data Index: 1302553 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.3314. Min Act: -0.1700

Data Index: 572024 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.3157. Min Act: -0.1700

Data Index: 888598 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.3157. Min Act: -0.1700

Data Index: 1317170 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.3471. Min Act: -0.1700

Data Index: 668973 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.2843. Min Act: -0.1700

Data Index: 465388 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.2843. Min Act: -0.1700

Data Index: 1067915 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.2686. Min Act: -0.1700

Data Index: 369346 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.2843. Min Act: -0.1700

Data Index: 270819 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.2529. Min Act: -0.1700

Data Index: 699724 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.2372. Min Act: -0.1700

Data Index: 1322566 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.2529. Min Act: -0.1700

Data Index: 1124008 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.1900. Min Act: -0.1700

Data Index: 301708 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.2372. Min Act: -0.1700

Data Index: 474535 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 3.5823. Min Range: -3.5823

Max Act: 3.2372. Min Act: -0.1700

Data Index: 343675 (C4 (Web Text))

Max Activating Token Index: 411