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

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

Neuron 588 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: 5.4810. Min Range: -5.4810

Max Act: 5.4810. Min Act: -0.1700

Data Index: 1305341 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 5.4810. Min Range: -5.4810

Max Act: 5.2935. Min Act: -0.1700

Data Index: 668713 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 5.4810. Min Range: -5.4810

Max Act: 5.2623. Min Act: -0.1700

Data Index: 296192 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 5.4810. Min Range: -5.4810

Max Act: 5.1685. Min Act: -0.1700

Data Index: 535600 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 5.4810. Min Range: -5.4810

Max Act: 5.1685. Min Act: -0.1700

Data Index: 448670 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 5.4810. Min Range: -5.4810

Max Act: 5.1998. Min Act: -0.1700

Data Index: 191681 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 5.4810. Min Range: -5.4810

Max Act: 5.1060. Min Act: -0.1700

Data Index: 489822 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 5.4810. Min Range: -5.4810

Max Act: 5.1685. Min Act: -0.1700

Data Index: 162294 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 5.4810. Min Range: -5.4810

Max Act: 5.1060. Min Act: -0.1700

Data Index: 981087 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 5.4810. Min Range: -5.4810

Max Act: 5.0748. Min Act: -0.1700

Data Index: 348477 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 5.4810. Min Range: -5.4810

Max Act: 4.9498. Min Act: -0.1700

Data Index: 416778 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 5.4810. Min Range: -5.4810

Max Act: 5.0435. Min Act: -0.1700

Data Index: 1043396 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 5.4810. Min Range: -5.4810

Max Act: 5.0435. Min Act: -0.1700

Data Index: 11747 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 5.4810. Min Range: -5.4810

Max Act: 5.0123. Min Act: -0.1700

Data Index: 532786 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 5.4810. Min Range: -5.4810

Max Act: 5.0435. Min Act: -0.1700

Data Index: 365377 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 5.4810. Min Range: -5.4810

Max Act: 4.9498. Min Act: -0.1700

Data Index: 137403 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 5.4810. Min Range: -5.4810

Max Act: 5.0123. Min Act: -0.1700

Data Index: 667722 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 5.4810. Min Range: -5.4810

Max Act: 5.0123. Min Act: -0.1700

Data Index: 220353 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 5.4810. Min Range: -5.4810

Max Act: 5.0123. Min Act: -0.1700

Data Index: 1348515 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 5.4810. Min Range: -5.4810

Max Act: 4.9185. Min Act: -0.1700

Data Index: 222454 (C4 (Web Text))

Max Activating Token Index: 82