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

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

Neuron 1534 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1496. Min Range: -3.1496

Max Act: 3.1496. Min Act: -0.1700

Data Index: 726185 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 3.1496. Min Range: -3.1496

Max Act: 3.1181. Min Act: -0.1700

Data Index: 1090683 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 3.1496. Min Range: -3.1496

Max Act: 3.0866. Min Act: -0.1700

Data Index: 1357226 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 3.1496. Min Range: -3.1496

Max Act: 3.1023. Min Act: -0.1700

Data Index: 1314289 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 3.1496. Min Range: -3.1496

Max Act: 3.1023. Min Act: -0.1700

Data Index: 512720 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 3.1496. Min Range: -3.1496

Max Act: 3.0866. Min Act: -0.1700

Data Index: 270402 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 3.1496. Min Range: -3.1496

Max Act: 3.0866. Min Act: -0.1700

Data Index: 1148583 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 3.1496. Min Range: -3.1496

Max Act: 3.0866. Min Act: -0.1700

Data Index: 714137 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 3.1496. Min Range: -3.1496

Max Act: 3.0866. Min Act: -0.1700

Data Index: 643892 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 3.1496. Min Range: -3.1496

Max Act: 3.0708. Min Act: -0.1700

Data Index: 414587 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 3.1496. Min Range: -3.1496

Max Act: 3.0708. Min Act: -0.1700

Data Index: 1166121 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 3.1496. Min Range: -3.1496

Max Act: 3.0708. Min Act: -0.1700

Data Index: 13432 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 3.1496. Min Range: -3.1496

Max Act: 3.0708. Min Act: -0.1700

Data Index: 127539 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 3.1496. Min Range: -3.1496

Max Act: 3.0708. Min Act: -0.1700

Data Index: 327041 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 3.1496. Min Range: -3.1496

Max Act: 3.0708. Min Act: -0.1700

Data Index: 29141 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 3.1496. Min Range: -3.1496

Max Act: 3.0550. Min Act: -0.1700

Data Index: 446355 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 3.1496. Min Range: -3.1496

Max Act: 3.0708. Min Act: -0.1700

Data Index: 1334891 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 3.1496. Min Range: -3.1496

Max Act: 3.0550. Min Act: -0.1700

Data Index: 756464 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 3.1496. Min Range: -3.1496

Max Act: 3.0550. Min Act: -0.1700

Data Index: 614490 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 3.1496. Min Range: -3.1496

Max Act: 3.0550. Min Act: -0.1700

Data Index: 292372 (C4 (Web Text))

Max Activating Token Index: 656