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

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

Neuron 1962 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.8541. Min Range: -3.8541

Max Act: 3.8541. Min Act: -0.1700

Data Index: 40677 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 3.8541. Min Range: -3.8541

Max Act: 3.8229. Min Act: -0.1700

Data Index: 61770 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 3.8541. Min Range: -3.8541

Max Act: 3.8229. Min Act: -0.1700

Data Index: 389893 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 3.8541. Min Range: -3.8541

Max Act: 3.7916. Min Act: -0.1700

Data Index: 595410 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 3.8541. Min Range: -3.8541

Max Act: 3.7916. Min Act: -0.1700

Data Index: 796556 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 3.8541. Min Range: -3.8541

Max Act: 3.7603. Min Act: -0.1700

Data Index: 982276 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 3.8541. Min Range: -3.8541

Max Act: 3.7603. Min Act: -0.1700

Data Index: 173068 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 3.8541. Min Range: -3.8541

Max Act: 3.7447. Min Act: -0.1700

Data Index: 251454 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 3.8541. Min Range: -3.8541

Max Act: 3.7290. Min Act: -0.1700

Data Index: 226524 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 3.8541. Min Range: -3.8541

Max Act: 3.7447. Min Act: -0.1700

Data Index: 1007069 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 3.8541. Min Range: -3.8541

Max Act: 3.7447. Min Act: -0.1700

Data Index: 442042 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 3.8541. Min Range: -3.8541

Max Act: 3.7603. Min Act: -0.1700

Data Index: 369067 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 3.8541. Min Range: -3.8541

Max Act: 3.7290. Min Act: -0.1700

Data Index: 767982 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 3.8541. Min Range: -3.8541

Max Act: 3.7134. Min Act: -0.1700

Data Index: 793787 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 3.8541. Min Range: -3.8541

Max Act: 3.6977. Min Act: -0.1700

Data Index: 1088651 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 3.8541. Min Range: -3.8541

Max Act: 3.6977. Min Act: -0.1700

Data Index: 633305 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 3.8541. Min Range: -3.8541

Max Act: 3.6977. Min Act: -0.1700

Data Index: 1244198 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 3.8541. Min Range: -3.8541

Max Act: 3.6977. Min Act: -0.1700

Data Index: 1138466 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 3.8541. Min Range: -3.8541

Max Act: 3.7134. Min Act: -0.1700

Data Index: 1317267 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 3.8541. Min Range: -3.8541

Max Act: 3.7134. Min Act: -0.1700

Data Index: 387930 (C4 (Web Text))

Max Activating Token Index: 150