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

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

Neuron 1000 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: 3.9367. Min Range: -3.9367

Max Act: 3.9367. Min Act: -0.1700

Data Index: 780095 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.9367. Min Act: -0.1700

Data Index: 756497 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.9054. Min Act: -0.1700

Data Index: 1194383 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.8429. Min Act: -0.1700

Data Index: 224967 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.8429. Min Act: -0.1700

Data Index: 635430 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.8741. Min Act: -0.1700

Data Index: 1255704 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.8741. Min Act: -0.1700

Data Index: 394573 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.8741. Min Act: -0.1700

Data Index: 244900 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.8429. Min Act: -0.1700

Data Index: 302439 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.8429. Min Act: -0.1700

Data Index: 234448 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.8116. Min Act: -0.1700

Data Index: 1063809 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.8116. Min Act: -0.1700

Data Index: 1010383 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.8429. Min Act: -0.1700

Data Index: 55873 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.8116. Min Act: -0.1700

Data Index: 304392 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.7803. Min Act: -0.1700

Data Index: 683952 (C4 (Web Text))

Max Activating Token Index: 117

Text #15

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.7803. Min Act: -0.1700

Data Index: 209990 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.8116. Min Act: -0.1700

Data Index: 848724 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.8116. Min Act: -0.1700

Data Index: 543550 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.8116. Min Act: -0.1700

Data Index: 325631 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.7803. Min Act: -0.1700

Data Index: 388704 (C4 (Web Text))

Max Activating Token Index: 272