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

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

Neuron 204 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.8215. Min Act: -0.1700

Data Index: 970558 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.8215. Min Act: -0.1700

Data Index: 1305562 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.8527. Min Act: -0.1700

Data Index: 398060 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.8527. Min Act: -0.1700

Data Index: 213455 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.8527. Min Act: -0.1700

Data Index: 539828 (C4 (Web Text))

Max Activating Token Index: 196

Text #5

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.8527. Min Act: -0.1700

Data Index: 859515 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.8215. Min Act: -0.1700

Data Index: 409856 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.7902. Min Act: -0.1700

Data Index: 713435 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.8215. Min Act: -0.1700

Data Index: 447134 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.8215. Min Act: -0.1700

Data Index: 1243204 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.7589. Min Act: -0.1700

Data Index: 771872 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.7902. Min Act: -0.1700

Data Index: 609184 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.7902. Min Act: -0.1700

Data Index: 905221 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.7902. Min Act: -0.1700

Data Index: 183952 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.7902. Min Act: -0.1700

Data Index: 312957 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.7902. Min Act: -0.1700

Data Index: 515721 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.8215. Min Act: -0.1700

Data Index: 450814 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.7902. Min Act: -0.1700

Data Index: 166154 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.8215. Min Act: -0.1700

Data Index: 770590 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 3.8527. Min Range: -3.8527

Max Act: 3.8215. Min Act: -0.1700

Data Index: 687833 (C4 (Web Text))

Max Activating Token Index: 961