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

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

Neuron 734 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: 3.2113. Min Range: -3.2113

Max Act: 3.2113. Min Act: -0.1700

Data Index: 579880 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 3.2113. Min Range: -3.2113

Max Act: 3.1799. Min Act: -0.1700

Data Index: 1258344 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 3.2113. Min Range: -3.2113

Max Act: 3.1484. Min Act: -0.1700

Data Index: 979347 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 3.2113. Min Range: -3.2113

Max Act: 3.1011. Min Act: -0.1700

Data Index: 110267 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 3.2113. Min Range: -3.2113

Max Act: 3.1326. Min Act: -0.1700

Data Index: 465729 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 3.2113. Min Range: -3.2113

Max Act: 3.1011. Min Act: -0.1700

Data Index: 214490 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 3.2113. Min Range: -3.2113

Max Act: 3.1169. Min Act: -0.1700

Data Index: 156434 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 3.2113. Min Range: -3.2113

Max Act: 3.1011. Min Act: -0.1700

Data Index: 542454 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 3.2113. Min Range: -3.2113

Max Act: 3.1011. Min Act: -0.1700

Data Index: 636240 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 3.2113. Min Range: -3.2113

Max Act: 3.0853. Min Act: -0.1700

Data Index: 295379 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 3.2113. Min Range: -3.2113

Max Act: 3.0853. Min Act: -0.1700

Data Index: 576132 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 3.2113. Min Range: -3.2113

Max Act: 3.0853. Min Act: -0.1700

Data Index: 955826 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 3.2113. Min Range: -3.2113

Max Act: 3.0538. Min Act: -0.1700

Data Index: 1250407 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 3.2113. Min Range: -3.2113

Max Act: 3.0538. Min Act: -0.1700

Data Index: 841634 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 3.2113. Min Range: -3.2113

Max Act: 3.0380. Min Act: -0.1700

Data Index: 558676 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 3.2113. Min Range: -3.2113

Max Act: 3.0538. Min Act: -0.1700

Data Index: 1109721 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 3.2113. Min Range: -3.2113

Max Act: 3.0538. Min Act: -0.1700

Data Index: 1154506 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 3.2113. Min Range: -3.2113

Max Act: 3.0380. Min Act: -0.1700

Data Index: 1082285 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 3.2113. Min Range: -3.2113

Max Act: 3.0538. Min Act: -0.1700

Data Index: 967242 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 3.2113. Min Range: -3.2113

Max Act: 3.0380. Min Act: -0.1700

Data Index: 100894 (C4 (Web Text))

Max Activating Token Index: 406