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

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

Neuron 522 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: 6.5555. Min Range: -6.5555

Max Act: 6.5555. Min Act: -0.1700

Data Index: 859755 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 6.5555. Min Range: -6.5555

Max Act: 6.2743. Min Act: -0.1700

Data Index: 502530 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 6.5555. Min Range: -6.5555

Max Act: 6.3055. Min Act: -0.1700

Data Index: 332433 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 6.5555. Min Range: -6.5555

Max Act: 6.1180. Min Act: -0.1700

Data Index: 676823 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 6.5555. Min Range: -6.5555

Max Act: 6.0868. Min Act: -0.1700

Data Index: 1152267 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 6.5555. Min Range: -6.5555

Max Act: 6.0243. Min Act: -0.1700

Data Index: 1052401 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 6.5555. Min Range: -6.5555

Max Act: 5.9618. Min Act: -0.1700

Data Index: 1111586 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 6.5555. Min Range: -6.5555

Max Act: 5.9930. Min Act: -0.1700

Data Index: 791439 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 6.5555. Min Range: -6.5555

Max Act: 5.8993. Min Act: -0.1700

Data Index: 955027 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 6.5555. Min Range: -6.5555

Max Act: 5.8680. Min Act: -0.1700

Data Index: 1132080 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 6.5555. Min Range: -6.5555

Max Act: 5.8055. Min Act: -0.1700

Data Index: 683963 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 6.5555. Min Range: -6.5555

Max Act: 5.8368. Min Act: -0.1700

Data Index: 180305 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 6.5555. Min Range: -6.5555

Max Act: 5.8368. Min Act: -0.1700

Data Index: 256602 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 6.5555. Min Range: -6.5555

Max Act: 5.7743. Min Act: -0.1700

Data Index: 1005881 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 6.5555. Min Range: -6.5555

Max Act: 5.8993. Min Act: -0.1700

Data Index: 1215338 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 6.5555. Min Range: -6.5555

Max Act: 5.8680. Min Act: -0.1700

Data Index: 1303261 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 6.5555. Min Range: -6.5555

Max Act: 5.7743. Min Act: -0.1700

Data Index: 789452 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 6.5555. Min Range: -6.5555

Max Act: 5.8055. Min Act: -0.1700

Data Index: 60725 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 6.5555. Min Range: -6.5555

Max Act: 5.8055. Min Act: -0.1700

Data Index: 611023 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 6.5555. Min Range: -6.5555

Max Act: 5.7743. Min Act: -0.1700

Data Index: 861896 (C4 (Web Text))

Max Activating Token Index: 591