Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 251 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6311. Min Range: -3.6311

Max Act: 3.6311. Min Act: -0.1700

Data Index: 1102603 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 3.6311. Min Range: -3.6311

Max Act: 3.6311. Min Act: -0.1700

Data Index: 837706 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 3.6311. Min Range: -3.6311

Max Act: 3.5685. Min Act: -0.1700

Data Index: 767820 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 3.6311. Min Range: -3.6311

Max Act: 3.5059. Min Act: -0.1700

Data Index: 147906 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 3.6311. Min Range: -3.6311

Max Act: 3.5372. Min Act: -0.1700

Data Index: 461615 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 3.6311. Min Range: -3.6311

Max Act: 3.4432. Min Act: -0.1700

Data Index: 485102 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 3.6311. Min Range: -3.6311

Max Act: 3.4745. Min Act: -0.1700

Data Index: 835300 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 3.6311. Min Range: -3.6311

Max Act: 3.4745. Min Act: -0.1700

Data Index: 938566 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 3.6311. Min Range: -3.6311

Max Act: 3.4432. Min Act: -0.1700

Data Index: 1087994 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 3.6311. Min Range: -3.6311

Max Act: 3.4745. Min Act: -0.1700

Data Index: 678413 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 3.6311. Min Range: -3.6311

Max Act: 3.4745. Min Act: -0.1700

Data Index: 269532 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 3.6311. Min Range: -3.6311

Max Act: 3.4745. Min Act: -0.1700

Data Index: 232124 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 3.6311. Min Range: -3.6311

Max Act: 3.4432. Min Act: -0.1700

Data Index: 1291295 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 3.6311. Min Range: -3.6311

Max Act: 3.4432. Min Act: -0.1700

Data Index: 481194 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 3.6311. Min Range: -3.6311

Max Act: 3.4118. Min Act: -0.1700

Data Index: 20645 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 3.6311. Min Range: -3.6311

Max Act: 3.4118. Min Act: -0.1700

Data Index: 879156 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 3.6311. Min Range: -3.6311

Max Act: 3.4118. Min Act: -0.1700

Data Index: 977925 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 3.6311. Min Range: -3.6311

Max Act: 3.3804. Min Act: -0.1700

Data Index: 1035694 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 3.6311. Min Range: -3.6311

Max Act: 3.4118. Min Act: -0.1700

Data Index: 707536 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 3.6311. Min Range: -3.6311

Max Act: 3.3804. Min Act: -0.1700

Data Index: 577461 (C4 (Web Text))

Max Activating Token Index: 968