Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1077 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 10.7251. Min Range: -10.7251

Max Act: 10.7251. Min Act: -0.1700

Data Index: 192478 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 10.7251. Min Range: -10.7251

Max Act: 10.6626. Min Act: -0.1700

Data Index: 1092021 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 10.7251. Min Range: -10.7251

Max Act: 10.4751. Min Act: -0.1699

Data Index: 147142 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 10.7251. Min Range: -10.7251

Max Act: 10.4126. Min Act: -0.1700

Data Index: 798122 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 10.7251. Min Range: -10.7251

Max Act: 10.3501. Min Act: -0.1699

Data Index: 1302831 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 10.7251. Min Range: -10.7251

Max Act: 10.3501. Min Act: -0.1699

Data Index: 163737 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 10.7251. Min Range: -10.7251

Max Act: 10.3501. Min Act: -0.1700

Data Index: 1087807 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 10.7251. Min Range: -10.7251

Max Act: 10.2251. Min Act: -0.1699

Data Index: 172233 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 10.7251. Min Range: -10.7251

Max Act: 10.1626. Min Act: -0.1700

Data Index: 80867 (C4 (Web Text))

Max Activating Token Index: 872

Text #9

Max Range: 10.7251. Min Range: -10.7251

Max Act: 10.2251. Min Act: -0.1700

Data Index: 917079 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 10.7251. Min Range: -10.7251

Max Act: 10.1626. Min Act: -0.1699

Data Index: 1187271 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 10.7251. Min Range: -10.7251

Max Act: 10.0376. Min Act: -0.1700

Data Index: 360658 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 10.7251. Min Range: -10.7251

Max Act: 10.1001. Min Act: -0.1700

Data Index: 1195979 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 10.7251. Min Range: -10.7251

Max Act: 10.1001. Min Act: -0.1700

Data Index: 256882 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 10.7251. Min Range: -10.7251

Max Act: 10.2251. Min Act: -0.1699

Data Index: 1035017 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 10.7251. Min Range: -10.7251

Max Act: 10.2251. Min Act: -0.1700

Data Index: 1117613 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 10.7251. Min Range: -10.7251

Max Act: 10.1001. Min Act: -0.1699

Data Index: 18644 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 10.7251. Min Range: -10.7251

Max Act: 10.1001. Min Act: -0.1680

Data Index: 555067 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 10.7251. Min Range: -10.7251

Max Act: 10.1001. Min Act: -0.1699

Data Index: 1024047 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 10.7251. Min Range: -10.7251

Max Act: 10.1001. Min Act: -0.1700

Data Index: 850218 (C4 (Web Text))

Max Activating Token Index: 871