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

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

Neuron 1248 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8856. Min Range: -5.8856

Max Act: 5.8544. Min Act: -0.1700

Data Index: 26831 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 5.8856. Min Range: -5.8856

Max Act: 5.8856. Min Act: -0.1700

Data Index: 541034 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 5.8856. Min Range: -5.8856

Max Act: 5.8231. Min Act: -0.1700

Data Index: 636434 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 5.8856. Min Range: -5.8856

Max Act: 5.7294. Min Act: -0.1700

Data Index: 23413 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 5.8856. Min Range: -5.8856

Max Act: 5.6669. Min Act: -0.1700

Data Index: 1164603 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 5.8856. Min Range: -5.8856

Max Act: 5.5731. Min Act: -0.1700

Data Index: 546345 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 5.8856. Min Range: -5.8856

Max Act: 5.6356. Min Act: -0.1700

Data Index: 1244225 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 5.8856. Min Range: -5.8856

Max Act: 5.5731. Min Act: -0.1700

Data Index: 474771 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 5.8856. Min Range: -5.8856

Max Act: 5.5731. Min Act: -0.1700

Data Index: 641038 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 5.8856. Min Range: -5.8856

Max Act: 5.4794. Min Act: -0.1700

Data Index: 604088 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 5.8856. Min Range: -5.8856

Max Act: 5.5419. Min Act: -0.1700

Data Index: 279809 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 5.8856. Min Range: -5.8856

Max Act: 5.5106. Min Act: -0.1700

Data Index: 387103 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 5.8856. Min Range: -5.8856

Max Act: 5.4169. Min Act: -0.1700

Data Index: 469142 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 5.8856. Min Range: -5.8856

Max Act: 5.4481. Min Act: -0.1700

Data Index: 1145208 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 5.8856. Min Range: -5.8856

Max Act: 5.4794. Min Act: -0.1700

Data Index: 161126 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 5.8856. Min Range: -5.8856

Max Act: 5.4481. Min Act: -0.1700

Data Index: 866041 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 5.8856. Min Range: -5.8856

Max Act: 5.4794. Min Act: -0.1700

Data Index: 20046 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 5.8856. Min Range: -5.8856

Max Act: 5.4481. Min Act: -0.1700

Data Index: 1140570 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 5.8856. Min Range: -5.8856

Max Act: 5.4169. Min Act: -0.1700

Data Index: 398189 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 5.8856. Min Range: -5.8856

Max Act: 5.4169. Min Act: -0.1700

Data Index: 539747 (C4 (Web Text))

Max Activating Token Index: 434