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

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

Neuron 1772 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: 3.9339. Min Range: -3.9339

Max Act: 3.9027. Min Act: -0.1700

Data Index: 192952 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 3.9339. Min Range: -3.9339

Max Act: 3.9339. Min Act: -0.1700

Data Index: 444818 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.9339. Min Range: -3.9339

Max Act: 3.7463. Min Act: -0.1700

Data Index: 536673 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 3.9339. Min Range: -3.9339

Max Act: 3.7150. Min Act: -0.1700

Data Index: 379495 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 3.9339. Min Range: -3.9339

Max Act: 3.7463. Min Act: -0.1700

Data Index: 765244 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 3.9339. Min Range: -3.9339

Max Act: 3.6211. Min Act: -0.1700

Data Index: 132611 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 3.9339. Min Range: -3.9339

Max Act: 3.6524. Min Act: -0.1700

Data Index: 419063 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 3.9339. Min Range: -3.9339

Max Act: 3.6524. Min Act: -0.1700

Data Index: 212061 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 3.9339. Min Range: -3.9339

Max Act: 3.6211. Min Act: -0.1700

Data Index: 861605 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 3.9339. Min Range: -3.9339

Max Act: 3.6524. Min Act: -0.1700

Data Index: 311714 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 3.9339. Min Range: -3.9339

Max Act: 3.5898. Min Act: -0.1700

Data Index: 94068 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 3.9339. Min Range: -3.9339

Max Act: 3.6524. Min Act: -0.1700

Data Index: 1019653 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 3.9339. Min Range: -3.9339

Max Act: 3.6211. Min Act: -0.1700

Data Index: 626228 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 3.9339. Min Range: -3.9339

Max Act: 3.5584. Min Act: -0.1700

Data Index: 425302 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 3.9339. Min Range: -3.9339

Max Act: 3.5584. Min Act: -0.1700

Data Index: 47572 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 3.9339. Min Range: -3.9339

Max Act: 3.4958. Min Act: -0.1700

Data Index: 1214141 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 3.9339. Min Range: -3.9339

Max Act: 3.4958. Min Act: -0.1700

Data Index: 388246 (C4 (Web Text))

Max Activating Token Index: 992

Text #17

Max Range: 3.9339. Min Range: -3.9339

Max Act: 3.5271. Min Act: -0.1700

Data Index: 976938 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 3.9339. Min Range: -3.9339

Max Act: 3.4958. Min Act: -0.1700

Data Index: 1014958 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 3.9339. Min Range: -3.9339

Max Act: 3.5584. Min Act: -0.1700

Data Index: 619042 (C4 (Web Text))

Max Activating Token Index: 432