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

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

Neuron 766 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: 5.4777. Min Range: -5.4777

Max Act: 5.2277. Min Act: -0.1700

Data Index: 370283 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 5.4777. Min Range: -5.4777

Max Act: 5.4777. Min Act: -0.1700

Data Index: 33980 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 5.4777. Min Range: -5.4777

Max Act: 5.0715. Min Act: -0.1700

Data Index: 464747 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 5.4777. Min Range: -5.4777

Max Act: 5.2277. Min Act: -0.1700

Data Index: 95137 (C4 (Web Text))

Max Activating Token Index: 975

Text #4

Max Range: 5.4777. Min Range: -5.4777

Max Act: 5.0090. Min Act: -0.1700

Data Index: 677432 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 5.4777. Min Range: -5.4777

Max Act: 4.9465. Min Act: -0.1700

Data Index: 155257 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 5.4777. Min Range: -5.4777

Max Act: 4.9465. Min Act: -0.1700

Data Index: 346149 (C4 (Web Text))

Max Activating Token Index: 371

Text #7

Max Range: 5.4777. Min Range: -5.4777

Max Act: 4.9777. Min Act: -0.1700

Data Index: 1276257 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 5.4777. Min Range: -5.4777

Max Act: 4.9465. Min Act: -0.1700

Data Index: 173158 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 5.4777. Min Range: -5.4777

Max Act: 4.8527. Min Act: -0.1700

Data Index: 773099 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 5.4777. Min Range: -5.4777

Max Act: 4.8840. Min Act: -0.1700

Data Index: 446931 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 5.4777. Min Range: -5.4777

Max Act: 4.8527. Min Act: -0.1700

Data Index: 702239 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 5.4777. Min Range: -5.4777

Max Act: 4.7902. Min Act: -0.1700

Data Index: 1105822 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 5.4777. Min Range: -5.4777

Max Act: 4.7902. Min Act: -0.1700

Data Index: 652597 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 5.4777. Min Range: -5.4777

Max Act: 4.7902. Min Act: -0.1700

Data Index: 47382 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 5.4777. Min Range: -5.4777

Max Act: 4.7590. Min Act: -0.1700

Data Index: 464969 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 5.4777. Min Range: -5.4777

Max Act: 4.7902. Min Act: -0.1700

Data Index: 1199293 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 5.4777. Min Range: -5.4777

Max Act: 4.7902. Min Act: -0.1700

Data Index: 634392 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 5.4777. Min Range: -5.4777

Max Act: 4.7902. Min Act: -0.1700

Data Index: 390197 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 5.4777. Min Range: -5.4777

Max Act: 4.7902. Min Act: -0.1700

Data Index: 81185 (C4 (Web Text))

Max Activating Token Index: 595