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

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

Neuron 2023 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3034. Min Range: -3.3034

Max Act: 3.3034. Min Act: -0.1700

Data Index: 957295 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 3.3034. Min Range: -3.3034

Max Act: 3.3034. Min Act: -0.1700

Data Index: 501787 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 3.3034. Min Range: -3.3034

Max Act: 3.3034. Min Act: -0.1700

Data Index: 1199475 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 3.3034. Min Range: -3.3034

Max Act: 3.2720. Min Act: -0.1700

Data Index: 574041 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 3.3034. Min Range: -3.3034

Max Act: 3.2720. Min Act: -0.1700

Data Index: 723554 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 3.3034. Min Range: -3.3034

Max Act: 3.2877. Min Act: -0.1700

Data Index: 1192851 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 3.3034. Min Range: -3.3034

Max Act: 3.2563. Min Act: -0.1700

Data Index: 691246 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 3.3034. Min Range: -3.3034

Max Act: 3.2563. Min Act: -0.1700

Data Index: 686139 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 3.3034. Min Range: -3.3034

Max Act: 3.2563. Min Act: -0.1700

Data Index: 1241363 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 3.3034. Min Range: -3.3034

Max Act: 3.2563. Min Act: -0.1700

Data Index: 277549 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 3.3034. Min Range: -3.3034

Max Act: 3.2720. Min Act: -0.1700

Data Index: 1324667 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 3.3034. Min Range: -3.3034

Max Act: 3.2563. Min Act: -0.1700

Data Index: 412357 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 3.3034. Min Range: -3.3034

Max Act: 3.2563. Min Act: -0.1700

Data Index: 826659 (C4 (Web Text))

Max Activating Token Index: 433

Text #13

Max Range: 3.3034. Min Range: -3.3034

Max Act: 3.2563. Min Act: -0.1700

Data Index: 29124 (C4 (Web Text))

Max Activating Token Index: 627

Text #14

Max Range: 3.3034. Min Range: -3.3034

Max Act: 3.2406. Min Act: -0.1700

Data Index: 597541 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 3.3034. Min Range: -3.3034

Max Act: 3.2248. Min Act: -0.1700

Data Index: 513376 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 3.3034. Min Range: -3.3034

Max Act: 3.2248. Min Act: -0.1700

Data Index: 51741 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 3.3034. Min Range: -3.3034

Max Act: 3.2406. Min Act: -0.1700

Data Index: 787277 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 3.3034. Min Range: -3.3034

Max Act: 3.2406. Min Act: -0.1700

Data Index: 978005 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 3.3034. Min Range: -3.3034

Max Act: 3.2248. Min Act: -0.1700

Data Index: 1006828 (C4 (Web Text))

Max Activating Token Index: 955