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

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

Neuron 590 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5087. Min Range: -3.5087

Max Act: 3.5087. Min Act: -0.1700

Data Index: 283384 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 3.5087. Min Range: -3.5087

Max Act: 3.4931. Min Act: -0.1700

Data Index: 700588 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 3.5087. Min Range: -3.5087

Max Act: 3.4617. Min Act: -0.1700

Data Index: 935675 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 3.5087. Min Range: -3.5087

Max Act: 3.4304. Min Act: -0.1700

Data Index: 215662 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 3.5087. Min Range: -3.5087

Max Act: 3.4304. Min Act: -0.1700

Data Index: 2651 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 3.5087. Min Range: -3.5087

Max Act: 3.4304. Min Act: -0.1700

Data Index: 190688 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 3.5087. Min Range: -3.5087

Max Act: 3.4147. Min Act: -0.1700

Data Index: 670540 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 3.5087. Min Range: -3.5087

Max Act: 3.3990. Min Act: -0.1700

Data Index: 903612 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 3.5087. Min Range: -3.5087

Max Act: 3.4147. Min Act: -0.1700

Data Index: 470747 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 3.5087. Min Range: -3.5087

Max Act: 3.3676. Min Act: -0.1700

Data Index: 1070015 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 3.5087. Min Range: -3.5087

Max Act: 3.3833. Min Act: -0.1700

Data Index: 469520 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 3.5087. Min Range: -3.5087

Max Act: 3.3519. Min Act: -0.1700

Data Index: 123809 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 3.5087. Min Range: -3.5087

Max Act: 3.3676. Min Act: -0.1700

Data Index: 219231 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 3.5087. Min Range: -3.5087

Max Act: 3.3362. Min Act: -0.1700

Data Index: 418613 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 3.5087. Min Range: -3.5087

Max Act: 3.3362. Min Act: -0.1700

Data Index: 905598 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 3.5087. Min Range: -3.5087

Max Act: 3.3048. Min Act: -0.1700

Data Index: 741701 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 3.5087. Min Range: -3.5087

Max Act: 3.3362. Min Act: -0.1700

Data Index: 25847 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 3.5087. Min Range: -3.5087

Max Act: 3.3362. Min Act: -0.1700

Data Index: 110246 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 3.5087. Min Range: -3.5087

Max Act: 3.3205. Min Act: -0.1700

Data Index: 520848 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 3.5087. Min Range: -3.5087

Max Act: 3.3205. Min Act: -0.1700

Data Index: 873772 (C4 (Web Text))

Max Activating Token Index: 85