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

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

Neuron 712 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7128. Min Range: -3.7128

Max Act: 3.6503. Min Act: -0.1700

Data Index: 748904 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 3.7128. Min Range: -3.7128

Max Act: 3.7128. Min Act: -0.1700

Data Index: 653758 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 3.7128. Min Range: -3.7128

Max Act: 3.6189. Min Act: -0.1700

Data Index: 274089 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 3.7128. Min Range: -3.7128

Max Act: 3.5876. Min Act: -0.1700

Data Index: 590353 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 3.7128. Min Range: -3.7128

Max Act: 3.6189. Min Act: -0.1700

Data Index: 544164 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 3.7128. Min Range: -3.7128

Max Act: 3.6503. Min Act: -0.1700

Data Index: 15278 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 3.7128. Min Range: -3.7128

Max Act: 3.5876. Min Act: -0.1700

Data Index: 1085245 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 3.7128. Min Range: -3.7128

Max Act: 3.5250. Min Act: -0.1700

Data Index: 154262 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 3.7128. Min Range: -3.7128

Max Act: 3.5876. Min Act: -0.1700

Data Index: 410506 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 3.7128. Min Range: -3.7128

Max Act: 3.5563. Min Act: -0.1700

Data Index: 734102 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 3.7128. Min Range: -3.7128

Max Act: 3.5563. Min Act: -0.1700

Data Index: 1058424 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 3.7128. Min Range: -3.7128

Max Act: 3.5876. Min Act: -0.1700

Data Index: 887974 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 3.7128. Min Range: -3.7128

Max Act: 3.5563. Min Act: -0.1700

Data Index: 1167552 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 3.7128. Min Range: -3.7128

Max Act: 3.5563. Min Act: -0.1700

Data Index: 1274546 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 3.7128. Min Range: -3.7128

Max Act: 3.5876. Min Act: -0.1700

Data Index: 274083 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 3.7128. Min Range: -3.7128

Max Act: 3.4936. Min Act: -0.1700

Data Index: 693001 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 3.7128. Min Range: -3.7128

Max Act: 3.5250. Min Act: -0.1700

Data Index: 958634 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 3.7128. Min Range: -3.7128

Max Act: 3.5250. Min Act: -0.1700

Data Index: 90239 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 3.7128. Min Range: -3.7128

Max Act: 3.5250. Min Act: -0.1700

Data Index: 845584 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 3.7128. Min Range: -3.7128

Max Act: 3.5250. Min Act: -0.1700

Data Index: 223704 (C4 (Web Text))

Max Activating Token Index: 83