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

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

Neuron 1033 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: 3.8256. Min Range: -3.8256

Max Act: 3.8256. Min Act: -0.1700

Data Index: 602254 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 3.8256. Min Range: -3.8256

Max Act: 3.7944. Min Act: -0.1700

Data Index: 420501 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 3.8256. Min Range: -3.8256

Max Act: 3.8256. Min Act: -0.1700

Data Index: 440734 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 3.8256. Min Range: -3.8256

Max Act: 3.7944. Min Act: -0.1700

Data Index: 284717 (C4 (Web Text))

Max Activating Token Index: 396

Text #4

Max Range: 3.8256. Min Range: -3.8256

Max Act: 3.7631. Min Act: -0.1700

Data Index: 1316126 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 3.8256. Min Range: -3.8256

Max Act: 3.7318. Min Act: -0.1700

Data Index: 539830 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 3.8256. Min Range: -3.8256

Max Act: 3.7318. Min Act: -0.1700

Data Index: 1032905 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 3.8256. Min Range: -3.8256

Max Act: 3.7631. Min Act: -0.1700

Data Index: 445538 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 3.8256. Min Range: -3.8256

Max Act: 3.7318. Min Act: -0.1700

Data Index: 1140554 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 3.8256. Min Range: -3.8256

Max Act: 3.7318. Min Act: -0.1700

Data Index: 1002023 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 3.8256. Min Range: -3.8256

Max Act: 3.7318. Min Act: -0.1700

Data Index: 462230 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 3.8256. Min Range: -3.8256

Max Act: 3.7005. Min Act: -0.1700

Data Index: 1243048 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 3.8256. Min Range: -3.8256

Max Act: 3.7318. Min Act: -0.1700

Data Index: 916460 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 3.8256. Min Range: -3.8256

Max Act: 3.7005. Min Act: -0.1700

Data Index: 17431 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 3.8256. Min Range: -3.8256

Max Act: 3.7005. Min Act: -0.1700

Data Index: 1081304 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 3.8256. Min Range: -3.8256

Max Act: 3.7005. Min Act: -0.1700

Data Index: 1072813 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 3.8256. Min Range: -3.8256

Max Act: 3.6692. Min Act: -0.1700

Data Index: 708892 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 3.8256. Min Range: -3.8256

Max Act: 3.7318. Min Act: -0.1700

Data Index: 672688 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 3.8256. Min Range: -3.8256

Max Act: 3.6692. Min Act: -0.1700

Data Index: 301844 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 3.8256. Min Range: -3.8256

Max Act: 3.7005. Min Act: -0.1700

Data Index: 298228 (C4 (Web Text))

Max Activating Token Index: 232