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

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

Neuron 729 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: 3.9599. Min Range: -3.9599

Max Act: 3.9599. Min Act: -0.1700

Data Index: 1057717 (C4 (Web Text))

Max Activating Token Index: 982

Text #1

Max Range: 3.9599. Min Range: -3.9599

Max Act: 3.9286. Min Act: -0.1700

Data Index: 324610 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 3.9599. Min Range: -3.9599

Max Act: 3.9599. Min Act: -0.1700

Data Index: 1100995 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 3.9599. Min Range: -3.9599

Max Act: 3.9599. Min Act: -0.1700

Data Index: 313295 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 3.9599. Min Range: -3.9599

Max Act: 3.8661. Min Act: -0.1700

Data Index: 46575 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 3.9599. Min Range: -3.9599

Max Act: 3.8348. Min Act: -0.1700

Data Index: 1117759 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 3.9599. Min Range: -3.9599

Max Act: 3.8035. Min Act: -0.1700

Data Index: 404987 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 3.9599. Min Range: -3.9599

Max Act: 3.8035. Min Act: -0.1700

Data Index: 1027200 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 3.9599. Min Range: -3.9599

Max Act: 3.8661. Min Act: -0.1700

Data Index: 39454 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 3.9599. Min Range: -3.9599

Max Act: 3.8348. Min Act: -0.1700

Data Index: 811250 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 3.9599. Min Range: -3.9599

Max Act: 3.7722. Min Act: -0.1700

Data Index: 1039106 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 3.9599. Min Range: -3.9599

Max Act: 3.8035. Min Act: -0.1700

Data Index: 796599 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 3.9599. Min Range: -3.9599

Max Act: 3.8348. Min Act: -0.1700

Data Index: 577710 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 3.9599. Min Range: -3.9599

Max Act: 3.8035. Min Act: -0.1700

Data Index: 1166224 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 3.9599. Min Range: -3.9599

Max Act: 3.7722. Min Act: -0.1700

Data Index: 1038503 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 3.9599. Min Range: -3.9599

Max Act: 3.8035. Min Act: -0.1700

Data Index: 90757 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 3.9599. Min Range: -3.9599

Max Act: 3.7410. Min Act: -0.1700

Data Index: 125945 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 3.9599. Min Range: -3.9599

Max Act: 3.7722. Min Act: -0.1700

Data Index: 205986 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 3.9599. Min Range: -3.9599

Max Act: 3.7722. Min Act: -0.1700

Data Index: 741018 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 3.9599. Min Range: -3.9599

Max Act: 3.7722. Min Act: -0.1700

Data Index: 774087 (C4 (Web Text))

Max Activating Token Index: 812