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

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

Neuron 740 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: 5.9645. Min Range: -5.9645

Max Act: 5.9645. Min Act: -0.1700

Data Index: 8878 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 5.9645. Min Range: -5.9645

Max Act: 5.7770. Min Act: -0.1700

Data Index: 997591 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 5.9645. Min Range: -5.9645

Max Act: 5.8082. Min Act: -0.1700

Data Index: 426934 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 5.9645. Min Range: -5.9645

Max Act: 5.7770. Min Act: -0.1700

Data Index: 856393 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 5.9645. Min Range: -5.9645

Max Act: 5.6207. Min Act: -0.1700

Data Index: 752823 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 5.9645. Min Range: -5.9645

Max Act: 5.6520. Min Act: -0.1700

Data Index: 544981 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 5.9645. Min Range: -5.9645

Max Act: 5.6207. Min Act: -0.1700

Data Index: 382579 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 5.9645. Min Range: -5.9645

Max Act: 5.5895. Min Act: -0.1700

Data Index: 392736 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 5.9645. Min Range: -5.9645

Max Act: 5.5895. Min Act: -0.1700

Data Index: 1278835 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 5.9645. Min Range: -5.9645

Max Act: 5.6207. Min Act: -0.1700

Data Index: 901807 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 5.9645. Min Range: -5.9645

Max Act: 5.6520. Min Act: -0.1700

Data Index: 966389 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 5.9645. Min Range: -5.9645

Max Act: 5.6207. Min Act: -0.1700

Data Index: 51707 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 5.9645. Min Range: -5.9645

Max Act: 5.5895. Min Act: -0.1700

Data Index: 477830 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 5.9645. Min Range: -5.9645

Max Act: 5.6207. Min Act: -0.1700

Data Index: 1156711 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 5.9645. Min Range: -5.9645

Max Act: 5.6207. Min Act: -0.1700

Data Index: 9996 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 5.9645. Min Range: -5.9645

Max Act: 5.5270. Min Act: -0.1700

Data Index: 659840 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 5.9645. Min Range: -5.9645

Max Act: 5.5895. Min Act: -0.1700

Data Index: 909099 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 5.9645. Min Range: -5.9645

Max Act: 5.5582. Min Act: -0.1700

Data Index: 282091 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 5.9645. Min Range: -5.9645

Max Act: 5.5895. Min Act: -0.1700

Data Index: 152306 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 5.9645. Min Range: -5.9645

Max Act: 5.5895. Min Act: -0.1700

Data Index: 1033642 (C4 (Web Text))

Max Activating Token Index: 267