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

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

Neuron 234 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.8011. Min Act: -0.1700

Data Index: 1190626 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.7072. Min Act: -0.1700

Data Index: 981376 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.6759. Min Act: -0.1700

Data Index: 415189 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.6446. Min Act: -0.1700

Data Index: 457726 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.5820. Min Act: -0.1700

Data Index: 176251 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.5507. Min Act: -0.1700

Data Index: 1356265 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.5193. Min Act: -0.1700

Data Index: 1274657 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.5507. Min Act: -0.1700

Data Index: 1284076 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.4880. Min Act: -0.1700

Data Index: 1190964 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.4880. Min Act: -0.1700

Data Index: 847380 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.4566. Min Act: -0.1700

Data Index: 1053061 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.4566. Min Act: -0.1700

Data Index: 739680 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.4880. Min Act: -0.1700

Data Index: 1017425 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.4566. Min Act: -0.1700

Data Index: 692094 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.4566. Min Act: -0.1700

Data Index: 500850 (C4 (Web Text))

Max Activating Token Index: 41

Text #15

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.4566. Min Act: -0.1700

Data Index: 78945 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.4566. Min Act: -0.1700

Data Index: 1145348 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.4566. Min Act: -0.1700

Data Index: 341051 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.3939. Min Act: -0.1700

Data Index: 849870 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 3.8011. Min Range: -3.8011

Max Act: 3.4253. Min Act: -0.1700

Data Index: 1173415 (C4 (Web Text))

Max Activating Token Index: 402