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

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

Neuron 1120 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2045. Min Range: -3.2045

Max Act: 3.2045. Min Act: -0.1700

Data Index: 424038 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 3.2045. Min Range: -3.2045

Max Act: 3.1573. Min Act: -0.1700

Data Index: 291402 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 3.2045. Min Range: -3.2045

Max Act: 3.1573. Min Act: -0.1700

Data Index: 744917 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 3.2045. Min Range: -3.2045

Max Act: 3.1416. Min Act: -0.1700

Data Index: 736387 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 3.2045. Min Range: -3.2045

Max Act: 3.1258. Min Act: -0.1700

Data Index: 599750 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 3.2045. Min Range: -3.2045

Max Act: 3.1101. Min Act: -0.1700

Data Index: 970100 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 3.2045. Min Range: -3.2045

Max Act: 3.1101. Min Act: -0.1700

Data Index: 796267 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 3.2045. Min Range: -3.2045

Max Act: 3.1101. Min Act: -0.1700

Data Index: 806076 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 3.2045. Min Range: -3.2045

Max Act: 3.0785. Min Act: -0.1700

Data Index: 396530 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 3.2045. Min Range: -3.2045

Max Act: 3.0785. Min Act: -0.1700

Data Index: 1183658 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 3.2045. Min Range: -3.2045

Max Act: 3.0785. Min Act: -0.1700

Data Index: 855357 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 3.2045. Min Range: -3.2045

Max Act: 3.0785. Min Act: -0.1700

Data Index: 798010 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 3.2045. Min Range: -3.2045

Max Act: 3.0628. Min Act: -0.1700

Data Index: 271013 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 3.2045. Min Range: -3.2045

Max Act: 3.0470. Min Act: -0.1700

Data Index: 1292405 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 3.2045. Min Range: -3.2045

Max Act: 3.0628. Min Act: -0.1700

Data Index: 278627 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 3.2045. Min Range: -3.2045

Max Act: 3.0785. Min Act: -0.1700

Data Index: 1115461 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 3.2045. Min Range: -3.2045

Max Act: 3.0628. Min Act: -0.1700

Data Index: 167522 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 3.2045. Min Range: -3.2045

Max Act: 3.0628. Min Act: -0.1700

Data Index: 1539710 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 3.2045. Min Range: -3.2045

Max Act: 3.0470. Min Act: -0.1700

Data Index: 451117 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 3.2045. Min Range: -3.2045

Max Act: 3.0628. Min Act: -0.1700

Data Index: 195505 (C4 (Web Text))

Max Activating Token Index: 45