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

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

Neuron 1059 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: 3.7222. Min Range: -3.7222

Max Act: 3.7222. Min Act: -0.1700

Data Index: 1132485 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 3.7222. Min Range: -3.7222

Max Act: 3.7222. Min Act: -0.1700

Data Index: 280339 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 3.7222. Min Range: -3.7222

Max Act: 3.6909. Min Act: -0.1700

Data Index: 1341421 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 3.7222. Min Range: -3.7222

Max Act: 3.7222. Min Act: -0.1700

Data Index: 1311482 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 3.7222. Min Range: -3.7222

Max Act: 3.5969. Min Act: -0.1700

Data Index: 1125705 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 3.7222. Min Range: -3.7222

Max Act: 3.6283. Min Act: -0.1700

Data Index: 692928 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 3.7222. Min Range: -3.7222

Max Act: 3.5969. Min Act: -0.1700

Data Index: 291721 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 3.7222. Min Range: -3.7222

Max Act: 3.5969. Min Act: -0.1700

Data Index: 669519 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 3.7222. Min Range: -3.7222

Max Act: 3.5969. Min Act: -0.1700

Data Index: 594264 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 3.7222. Min Range: -3.7222

Max Act: 3.5969. Min Act: -0.1700

Data Index: 1058506 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 3.7222. Min Range: -3.7222

Max Act: 3.5030. Min Act: -0.1700

Data Index: 794719 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 3.7222. Min Range: -3.7222

Max Act: 3.5030. Min Act: -0.1700

Data Index: 390604 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 3.7222. Min Range: -3.7222

Max Act: 3.4716. Min Act: -0.1700

Data Index: 1019350 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 3.7222. Min Range: -3.7222

Max Act: 3.4716. Min Act: -0.1700

Data Index: 470549 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 3.7222. Min Range: -3.7222

Max Act: 3.4716. Min Act: -0.1700

Data Index: 460843 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 3.7222. Min Range: -3.7222

Max Act: 3.4716. Min Act: -0.1700

Data Index: 875390 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 3.7222. Min Range: -3.7222

Max Act: 3.4716. Min Act: -0.1700

Data Index: 7551 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 3.7222. Min Range: -3.7222

Max Act: 3.4716. Min Act: -0.1700

Data Index: 551490 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 3.7222. Min Range: -3.7222

Max Act: 3.4716. Min Act: -0.1700

Data Index: 936153 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 3.7222. Min Range: -3.7222

Max Act: 3.4089. Min Act: -0.1700

Data Index: 607333 (C4 (Web Text))

Max Activating Token Index: 580