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

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

Neuron 387 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.5951. Min Range: -5.5951

Max Act: 5.5951. Min Act: -0.1700

Data Index: 344994 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 5.5951. Min Range: -5.5951

Max Act: 5.2513. Min Act: -0.1700

Data Index: 1230843 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 5.5951. Min Range: -5.5951

Max Act: 5.2201. Min Act: -0.1700

Data Index: 1124114 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 5.5951. Min Range: -5.5951

Max Act: 5.2513. Min Act: -0.1700

Data Index: 863297 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 5.5951. Min Range: -5.5951

Max Act: 5.2513. Min Act: -0.1700

Data Index: 931071 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 5.5951. Min Range: -5.5951

Max Act: 5.2201. Min Act: -0.1700

Data Index: 424804 (C4 (Web Text))

Max Activating Token Index: 653

Text #6

Max Range: 5.5951. Min Range: -5.5951

Max Act: 5.1888. Min Act: -0.1700

Data Index: 1060208 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 5.5951. Min Range: -5.5951

Max Act: 5.1888. Min Act: -0.1700

Data Index: 1314239 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 5.5951. Min Range: -5.5951

Max Act: 5.1576. Min Act: -0.1700

Data Index: 310241 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 5.5951. Min Range: -5.5951

Max Act: 5.1888. Min Act: -0.1700

Data Index: 1161050 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 5.5951. Min Range: -5.5951

Max Act: 5.2513. Min Act: -0.1700

Data Index: 80502 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 5.5951. Min Range: -5.5951

Max Act: 5.1576. Min Act: -0.1700

Data Index: 751883 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 5.5951. Min Range: -5.5951

Max Act: 5.0951. Min Act: -0.1700

Data Index: 1013428 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 5.5951. Min Range: -5.5951

Max Act: 5.1576. Min Act: -0.1700

Data Index: 1321418 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 5.5951. Min Range: -5.5951

Max Act: 5.1263. Min Act: -0.1700

Data Index: 393657 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 5.5951. Min Range: -5.5951

Max Act: 5.0638. Min Act: -0.1700

Data Index: 742140 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 5.5951. Min Range: -5.5951

Max Act: 5.0951. Min Act: -0.1700

Data Index: 856187 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 5.5951. Min Range: -5.5951

Max Act: 5.0638. Min Act: -0.1700

Data Index: 1271505 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 5.5951. Min Range: -5.5951

Max Act: 5.0326. Min Act: -0.1700

Data Index: 1170818 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 5.5951. Min Range: -5.5951

Max Act: 5.0013. Min Act: -0.1700

Data Index: 910944 (C4 (Web Text))

Max Activating Token Index: 391