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

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

Neuron 976 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: 3.9748. Min Range: -3.9748

Max Act: 3.9748. Min Act: -0.1700

Data Index: 752836 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 3.9748. Min Range: -3.9748

Max Act: 3.9435. Min Act: -0.1700

Data Index: 1076396 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 3.9748. Min Range: -3.9748

Max Act: 3.9435. Min Act: -0.1700

Data Index: 1065474 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 3.9748. Min Range: -3.9748

Max Act: 3.9122. Min Act: -0.1700

Data Index: 908599 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 3.9748. Min Range: -3.9748

Max Act: 3.8810. Min Act: -0.1700

Data Index: 345083 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 3.9748. Min Range: -3.9748

Max Act: 3.8810. Min Act: -0.1700

Data Index: 789523 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 3.9748. Min Range: -3.9748

Max Act: 3.8497. Min Act: -0.1700

Data Index: 646828 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 3.9748. Min Range: -3.9748

Max Act: 3.8497. Min Act: -0.1700

Data Index: 779477 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 3.9748. Min Range: -3.9748

Max Act: 3.8497. Min Act: -0.1700

Data Index: 1063933 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 3.9748. Min Range: -3.9748

Max Act: 3.8497. Min Act: -0.1700

Data Index: 588182 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 3.9748. Min Range: -3.9748

Max Act: 3.8497. Min Act: -0.1700

Data Index: 494486 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 3.9748. Min Range: -3.9748

Max Act: 3.8497. Min Act: -0.1700

Data Index: 1211139 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 3.9748. Min Range: -3.9748

Max Act: 3.8497. Min Act: -0.1700

Data Index: 1116212 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 3.9748. Min Range: -3.9748

Max Act: 3.8497. Min Act: -0.1700

Data Index: 1086733 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 3.9748. Min Range: -3.9748

Max Act: 3.8184. Min Act: -0.1700

Data Index: 1276783 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 3.9748. Min Range: -3.9748

Max Act: 3.8497. Min Act: -0.1700

Data Index: 635954 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 3.9748. Min Range: -3.9748

Max Act: 3.8184. Min Act: -0.1700

Data Index: 585174 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 3.9748. Min Range: -3.9748

Max Act: 3.7871. Min Act: -0.1700

Data Index: 926972 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 3.9748. Min Range: -3.9748

Max Act: 3.7559. Min Act: -0.1700

Data Index: 929645 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 3.9748. Min Range: -3.9748

Max Act: 3.7871. Min Act: -0.1700

Data Index: 962579 (C4 (Web Text))

Max Activating Token Index: 741