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

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

Neuron 1110 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: 5.7059. Min Range: -5.7059

Max Act: 5.6434. Min Act: -0.1700

Data Index: 941143 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 5.7059. Min Range: -5.7059

Max Act: 5.6434. Min Act: -0.1700

Data Index: 233060 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 5.7059. Min Range: -5.7059

Max Act: 5.7059. Min Act: -0.1700

Data Index: 57888 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 5.7059. Min Range: -5.7059

Max Act: 5.7059. Min Act: -0.1700

Data Index: 911478 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 5.7059. Min Range: -5.7059

Max Act: 5.6122. Min Act: -0.1700

Data Index: 70195 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 5.7059. Min Range: -5.7059

Max Act: 5.6434. Min Act: -0.1700

Data Index: 157709 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 5.7059. Min Range: -5.7059

Max Act: 5.5497. Min Act: -0.1700

Data Index: 1041651 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 5.7059. Min Range: -5.7059

Max Act: 5.5809. Min Act: -0.1700

Data Index: 957221 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 5.7059. Min Range: -5.7059

Max Act: 5.6122. Min Act: -0.1700

Data Index: 1200075 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 5.7059. Min Range: -5.7059

Max Act: 5.5184. Min Act: -0.1700

Data Index: 606598 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 5.7059. Min Range: -5.7059

Max Act: 5.5184. Min Act: -0.1700

Data Index: 327484 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 5.7059. Min Range: -5.7059

Max Act: 5.5184. Min Act: -0.1700

Data Index: 578180 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 5.7059. Min Range: -5.7059

Max Act: 5.5497. Min Act: -0.1700

Data Index: 817443 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 5.7059. Min Range: -5.7059

Max Act: 5.5497. Min Act: -0.1700

Data Index: 263355 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 5.7059. Min Range: -5.7059

Max Act: 5.5497. Min Act: -0.1700

Data Index: 150337 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 5.7059. Min Range: -5.7059

Max Act: 5.5809. Min Act: -0.1700

Data Index: 521384 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 5.7059. Min Range: -5.7059

Max Act: 5.5184. Min Act: -0.1700

Data Index: 531616 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 5.7059. Min Range: -5.7059

Max Act: 5.4559. Min Act: -0.1700

Data Index: 74328 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 5.7059. Min Range: -5.7059

Max Act: 5.3622. Min Act: -0.1700

Data Index: 897464 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 5.7059. Min Range: -5.7059

Max Act: 5.6122. Min Act: -0.1700

Data Index: 566782 (C4 (Web Text))

Max Activating Token Index: 406