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

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

Neuron 533 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: 4.2604. Min Range: -4.2604

Max Act: 4.2604. Min Act: -0.1700

Data Index: 629529 (C4 (Web Text))

Max Activating Token Index: 293

Text #1

Max Range: 4.2604. Min Range: -4.2604

Max Act: 4.1354. Min Act: -0.1700

Data Index: 819442 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 4.2604. Min Range: -4.2604

Max Act: 4.1354. Min Act: -0.1700

Data Index: 10520 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 4.2604. Min Range: -4.2604

Max Act: 4.1041. Min Act: -0.1700

Data Index: 450517 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 4.2604. Min Range: -4.2604

Max Act: 4.1041. Min Act: -0.1700

Data Index: 588237 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 4.2604. Min Range: -4.2604

Max Act: 4.0103. Min Act: -0.1700

Data Index: 673983 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 4.2604. Min Range: -4.2604

Max Act: 4.0103. Min Act: -0.1700

Data Index: 742487 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 4.2604. Min Range: -4.2604

Max Act: 4.0416. Min Act: -0.1700

Data Index: 739902 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 4.2604. Min Range: -4.2604

Max Act: 4.0416. Min Act: -0.1700

Data Index: 1319459 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 4.2604. Min Range: -4.2604

Max Act: 4.0729. Min Act: -0.1700

Data Index: 1347441 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 4.2604. Min Range: -4.2604

Max Act: 4.0103. Min Act: -0.1700

Data Index: 588232 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 4.2604. Min Range: -4.2604

Max Act: 4.0103. Min Act: -0.1700

Data Index: 262721 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 4.2604. Min Range: -4.2604

Max Act: 4.0103. Min Act: -0.1700

Data Index: 923736 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 4.2604. Min Range: -4.2604

Max Act: 3.9791. Min Act: -0.1700

Data Index: 927842 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 4.2604. Min Range: -4.2604

Max Act: 3.9165. Min Act: -0.1700

Data Index: 182667 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 4.2604. Min Range: -4.2604

Max Act: 3.9478. Min Act: -0.1700

Data Index: 316743 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 4.2604. Min Range: -4.2604

Max Act: 3.9791. Min Act: -0.1700

Data Index: 413979 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 4.2604. Min Range: -4.2604

Max Act: 3.9478. Min Act: -0.1700

Data Index: 739223 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 4.2604. Min Range: -4.2604

Max Act: 3.9165. Min Act: -0.1700

Data Index: 124986 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 4.2604. Min Range: -4.2604

Max Act: 3.9165. Min Act: -0.1700

Data Index: 1217897 (C4 (Web Text))

Max Activating Token Index: 563