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

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

Neuron 1734 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: 5.5255. Min Range: -5.5255

Max Act: 5.5255. Min Act: -0.1700

Data Index: 868150 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 5.5255. Min Range: -5.5255

Max Act: 5.3380. Min Act: -0.1700

Data Index: 1245468 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 5.5255. Min Range: -5.5255

Max Act: 5.2755. Min Act: -0.1700

Data Index: 59694 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 5.5255. Min Range: -5.5255

Max Act: 5.3067. Min Act: -0.1700

Data Index: 766452 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 5.5255. Min Range: -5.5255

Max Act: 5.2442. Min Act: -0.1700

Data Index: 143037 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 5.5255. Min Range: -5.5255

Max Act: 5.2755. Min Act: -0.1700

Data Index: 551514 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 5.5255. Min Range: -5.5255

Max Act: 5.1817. Min Act: -0.1700

Data Index: 1033451 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 5.5255. Min Range: -5.5255

Max Act: 5.2442. Min Act: -0.1700

Data Index: 1148099 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 5.5255. Min Range: -5.5255

Max Act: 5.1192. Min Act: -0.1700

Data Index: 930391 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 5.5255. Min Range: -5.5255

Max Act: 5.1192. Min Act: -0.1700

Data Index: 253777 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 5.5255. Min Range: -5.5255

Max Act: 5.1192. Min Act: -0.1700

Data Index: 954998 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 5.5255. Min Range: -5.5255

Max Act: 5.0567. Min Act: -0.1700

Data Index: 913418 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 5.5255. Min Range: -5.5255

Max Act: 5.0880. Min Act: -0.1700

Data Index: 1131055 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 5.5255. Min Range: -5.5255

Max Act: 5.0255. Min Act: -0.1700

Data Index: 245761 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 5.5255. Min Range: -5.5255

Max Act: 5.0880. Min Act: -0.1700

Data Index: 888486 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 5.5255. Min Range: -5.5255

Max Act: 5.0255. Min Act: -0.1700

Data Index: 177088 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 5.5255. Min Range: -5.5255

Max Act: 5.0255. Min Act: -0.1700

Data Index: 132433 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 5.5255. Min Range: -5.5255

Max Act: 5.0255. Min Act: -0.1699

Data Index: 1181876 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 5.5255. Min Range: -5.5255

Max Act: 5.0255. Min Act: -0.1700

Data Index: 811554 (C4 (Web Text))

Max Activating Token Index: 963

Text #19

Max Range: 5.5255. Min Range: -5.5255

Max Act: 4.9630. Min Act: -0.1700

Data Index: 739106 (C4 (Web Text))

Max Activating Token Index: 618