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

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

Neuron 771 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7791. Min Range: -3.7791

Max Act: 3.7791. Min Act: -0.1700

Data Index: 440682 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 3.7791. Min Range: -3.7791

Max Act: 3.7635. Min Act: -0.1700

Data Index: 1242957 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 3.7791. Min Range: -3.7791

Max Act: 3.7635. Min Act: -0.1700

Data Index: 1429905 (Python Code)

Max Activating Token Index: 677

Text #3

Max Range: 3.7791. Min Range: -3.7791

Max Act: 3.6853. Min Act: -0.1700

Data Index: 567016 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 3.7791. Min Range: -3.7791

Max Act: 3.6853. Min Act: -0.1700

Data Index: 576908 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 3.7791. Min Range: -3.7791

Max Act: 3.6853. Min Act: -0.1700

Data Index: 934759 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 3.7791. Min Range: -3.7791

Max Act: 3.7009. Min Act: -0.1700

Data Index: 1162403 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 3.7791. Min Range: -3.7791

Max Act: 3.7166. Min Act: -0.1700

Data Index: 1578369 (Python Code)

Max Activating Token Index: 576

Text #8

Max Range: 3.7791. Min Range: -3.7791

Max Act: 3.6696. Min Act: -0.1700

Data Index: 163229 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 3.7791. Min Range: -3.7791

Max Act: 3.7166. Min Act: -0.1700

Data Index: 507922 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 3.7791. Min Range: -3.7791

Max Act: 3.6540. Min Act: -0.1700

Data Index: 1196495 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 3.7791. Min Range: -3.7791

Max Act: 3.6696. Min Act: -0.1700

Data Index: 36395 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 3.7791. Min Range: -3.7791

Max Act: 3.6070. Min Act: -0.1700

Data Index: 802045 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 3.7791. Min Range: -3.7791

Max Act: 3.6383. Min Act: -0.1700

Data Index: 1302415 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 3.7791. Min Range: -3.7791

Max Act: 3.6227. Min Act: -0.1700

Data Index: 797257 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 3.7791. Min Range: -3.7791

Max Act: 3.6070. Min Act: -0.1700

Data Index: 1195601 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 3.7791. Min Range: -3.7791

Max Act: 3.6383. Min Act: -0.1700

Data Index: 1180672 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 3.7791. Min Range: -3.7791

Max Act: 3.6227. Min Act: -0.1700

Data Index: 935680 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 3.7791. Min Range: -3.7791

Max Act: 3.6070. Min Act: -0.1700

Data Index: 693629 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 3.7791. Min Range: -3.7791

Max Act: 3.6227. Min Act: -0.1700

Data Index: 512520 (C4 (Web Text))

Max Activating Token Index: 682