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

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

Neuron 1755 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: 3.8500. Min Range: -3.8500

Max Act: 3.8500. Min Act: -0.1700

Data Index: 869052 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.8187. Min Act: -0.1700

Data Index: 1101721 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.7875. Min Act: -0.1700

Data Index: 145595 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.6936. Min Act: -0.1700

Data Index: 545148 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.7249. Min Act: -0.1700

Data Index: 408103 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.6936. Min Act: -0.1700

Data Index: 737198 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.6936. Min Act: -0.1700

Data Index: 556026 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.7249. Min Act: -0.1700

Data Index: 98263 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.6936. Min Act: -0.1700

Data Index: 244623 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.6936. Min Act: -0.1700

Data Index: 84317 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.6623. Min Act: -0.1700

Data Index: 81619 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.6936. Min Act: -0.1700

Data Index: 516242 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.6623. Min Act: -0.1700

Data Index: 1171720 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.6623. Min Act: -0.1700

Data Index: 1369876 (Python Code)

Max Activating Token Index: 405

Text #14

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.6310. Min Act: -0.1700

Data Index: 558039 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.6310. Min Act: -0.1700

Data Index: 1033228 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.6936. Min Act: -0.1700

Data Index: 1254470 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.6623. Min Act: -0.1700

Data Index: 575269 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.6310. Min Act: -0.1700

Data Index: 1358043 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 3.8500. Min Range: -3.8500

Max Act: 3.6623. Min Act: -0.1700

Data Index: 185195 (C4 (Web Text))

Max Activating Token Index: 912