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

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

Neuron 1914 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.3264. Min Act: -0.1700

Data Index: 1650151 (Python Code)

Max Activating Token Index: 2

Text #1

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.3107. Min Act: -0.1700

Data Index: 930270 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.2950. Min Act: -0.1700

Data Index: 659357 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.2636. Min Act: -0.1700

Data Index: 1109216 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.2479. Min Act: -0.1700

Data Index: 389317 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.2479. Min Act: -0.1700

Data Index: 1548814 (Python Code)

Max Activating Token Index: 35

Text #6

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.2479. Min Act: -0.1700

Data Index: 125082 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.1849. Min Act: -0.1700

Data Index: 463108 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.1692. Min Act: -0.1700

Data Index: 1379990 (Python Code)

Max Activating Token Index: 828

Text #9

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.1849. Min Act: -0.1700

Data Index: 1361056 (Python Code)

Max Activating Token Index: 171

Text #10

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.1220. Min Act: -0.1700

Data Index: 1647566 (Python Code)

Max Activating Token Index: 4

Text #11

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.1220. Min Act: -0.1700

Data Index: 332752 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.1062. Min Act: -0.1700

Data Index: 847587 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.1220. Min Act: -0.1700

Data Index: 553961 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.0904. Min Act: -0.1700

Data Index: 987121 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.1062. Min Act: -0.1700

Data Index: 309498 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.0747. Min Act: -0.1700

Data Index: 567986 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.0589. Min Act: -0.1700

Data Index: 828641 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.0747. Min Act: -0.1700

Data Index: 900646 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 3.3264. Min Range: -3.3264

Max Act: 3.0589. Min Act: -0.1700

Data Index: 1137179 (C4 (Web Text))

Max Activating Token Index: 629