Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 431 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.3968. Min Act: -0.1700

Data Index: 356143 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.3497. Min Act: -0.1700

Data Index: 777980 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.3183. Min Act: -0.1700

Data Index: 6499 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.3183. Min Act: -0.1700

Data Index: 1851 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.3183. Min Act: -0.1700

Data Index: 381898 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2869. Min Act: -0.1700

Data Index: 1010595 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2869. Min Act: -0.1700

Data Index: 755910 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2712. Min Act: -0.1700

Data Index: 150625 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2555. Min Act: -0.1700

Data Index: 133100 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2555. Min Act: -0.1700

Data Index: 476433 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2555. Min Act: -0.1700

Data Index: 1077349 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2712. Min Act: -0.1700

Data Index: 1045814 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2398. Min Act: -0.1700

Data Index: 434784 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2398. Min Act: -0.1700

Data Index: 1038148 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2398. Min Act: -0.1700

Data Index: 1313818 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2083. Min Act: -0.1700

Data Index: 1070907 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2398. Min Act: -0.1700

Data Index: 473519 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2240. Min Act: -0.1700

Data Index: 797152 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2083. Min Act: -0.1700

Data Index: 323509 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2083. Min Act: -0.1700

Data Index: 65777 (C4 (Web Text))

Max Activating Token Index: 184