Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1101 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 10.8477. Min Range: -10.8477

Max Act: 10.8477. Min Act: -0.1700

Data Index: 891611 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 10.8477. Min Range: -10.8477

Max Act: 10.5352. Min Act: -0.1700

Data Index: 1049809 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 10.8477. Min Range: -10.8477

Max Act: 10.0352. Min Act: -0.1700

Data Index: 980975 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 10.8477. Min Range: -10.8477

Max Act: 10.1602. Min Act: -0.1700

Data Index: 81444 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 10.8477. Min Range: -10.8477

Max Act: 10.0977. Min Act: -0.1700

Data Index: 1094050 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 10.8477. Min Range: -10.8477

Max Act: 9.9727. Min Act: -0.1700

Data Index: 376556 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 10.8477. Min Range: -10.8477

Max Act: 9.8477. Min Act: -0.1700

Data Index: 467256 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 10.8477. Min Range: -10.8477

Max Act: 9.8477. Min Act: -0.1700

Data Index: 4636 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 10.8477. Min Range: -10.8477

Max Act: 9.7227. Min Act: -0.1698

Data Index: 122267 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 10.8477. Min Range: -10.8477

Max Act: 9.8477. Min Act: -0.1700

Data Index: 428165 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 10.8477. Min Range: -10.8477

Max Act: 9.7227. Min Act: -0.1700

Data Index: 807044 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 10.8477. Min Range: -10.8477

Max Act: 9.7227. Min Act: -0.1700

Data Index: 1329481 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 10.8477. Min Range: -10.8477

Max Act: 9.6602. Min Act: -0.1697

Data Index: 370922 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 10.8477. Min Range: -10.8477

Max Act: 9.7852. Min Act: -0.1700

Data Index: 1090561 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 10.8477. Min Range: -10.8477

Max Act: 9.7227. Min Act: -0.1700

Data Index: 728070 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 10.8477. Min Range: -10.8477

Max Act: 9.7227. Min Act: -0.1700

Data Index: 1243666 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 10.8477. Min Range: -10.8477

Max Act: 9.7852. Min Act: -0.1695

Data Index: 286213 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 10.8477. Min Range: -10.8477

Max Act: 9.6602. Min Act: -0.1700

Data Index: 555893 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 10.8477. Min Range: -10.8477

Max Act: 9.5352. Min Act: -0.1700

Data Index: 1075111 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 10.8477. Min Range: -10.8477

Max Act: 9.5977. Min Act: -0.1699

Data Index: 499878 (C4 (Web Text))

Max Activating Token Index: 563