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

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

Neuron 34 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0905. Min Range: -3.0905

Max Act: 3.0905. Min Act: -0.1700

Data Index: 335810 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 3.0905. Min Range: -3.0905

Max Act: 3.0432. Min Act: -0.1700

Data Index: 948679 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 3.0905. Min Range: -3.0905

Max Act: 3.0116. Min Act: -0.1700

Data Index: 220026 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 3.0905. Min Range: -3.0905

Max Act: 2.9958. Min Act: -0.1700

Data Index: 1107307 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 3.0905. Min Range: -3.0905

Max Act: 3.0116. Min Act: -0.1700

Data Index: 254656 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 3.0905. Min Range: -3.0905

Max Act: 2.9800. Min Act: -0.1700

Data Index: 354629 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 3.0905. Min Range: -3.0905

Max Act: 3.0432. Min Act: -0.1700

Data Index: 924496 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 3.0905. Min Range: -3.0905

Max Act: 2.9958. Min Act: -0.1700

Data Index: 593995 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 3.0905. Min Range: -3.0905

Max Act: 2.9641. Min Act: -0.1700

Data Index: 477713 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 3.0905. Min Range: -3.0905

Max Act: 2.9800. Min Act: -0.1700

Data Index: 720986 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 3.0905. Min Range: -3.0905

Max Act: 2.9800. Min Act: -0.1700

Data Index: 284991 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 3.0905. Min Range: -3.0905

Max Act: 2.9641. Min Act: -0.1700

Data Index: 860377 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 3.0905. Min Range: -3.0905

Max Act: 2.9483. Min Act: -0.1700

Data Index: 1193033 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 3.0905. Min Range: -3.0905

Max Act: 2.9325. Min Act: -0.1700

Data Index: 334154 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 3.0905. Min Range: -3.0905

Max Act: 2.9325. Min Act: -0.1700

Data Index: 676160 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 3.0905. Min Range: -3.0905

Max Act: 2.9325. Min Act: -0.1700

Data Index: 1243575 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 3.0905. Min Range: -3.0905

Max Act: 2.9325. Min Act: -0.1700

Data Index: 995926 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 3.0905. Min Range: -3.0905

Max Act: 2.9325. Min Act: -0.1700

Data Index: 640162 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 3.0905. Min Range: -3.0905

Max Act: 2.9325. Min Act: -0.1700

Data Index: 548840 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 3.0905. Min Range: -3.0905

Max Act: 2.9008. Min Act: -0.1700

Data Index: 829683 (C4 (Web Text))

Max Activating Token Index: 246