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

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

Neuron 282 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: 3.6229. Min Range: -3.6229

Max Act: 3.6229. Min Act: -0.1700

Data Index: 797023 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 3.6229. Min Range: -3.6229

Max Act: 3.4976. Min Act: -0.1700

Data Index: 1231542 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 3.6229. Min Range: -3.6229

Max Act: 3.4506. Min Act: -0.1700

Data Index: 212878 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 3.6229. Min Range: -3.6229

Max Act: 3.3722. Min Act: -0.1700

Data Index: 789172 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 3.6229. Min Range: -3.6229

Max Act: 3.2623. Min Act: -0.1700

Data Index: 467782 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 3.6229. Min Range: -3.6229

Max Act: 3.1994. Min Act: -0.1700

Data Index: 920808 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 3.6229. Min Range: -3.6229

Max Act: 3.1836. Min Act: -0.1700

Data Index: 1284564 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 3.6229. Min Range: -3.6229

Max Act: 3.1836. Min Act: -0.1700

Data Index: 125560 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 3.6229. Min Range: -3.6229

Max Act: 3.1522. Min Act: -0.1700

Data Index: 839336 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 3.6229. Min Range: -3.6229

Max Act: 3.1679. Min Act: -0.1700

Data Index: 411257 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 3.6229. Min Range: -3.6229

Max Act: 3.1522. Min Act: -0.1700

Data Index: 1249574 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 3.6229. Min Range: -3.6229

Max Act: 3.1522. Min Act: -0.1700

Data Index: 690560 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 3.6229. Min Range: -3.6229

Max Act: 3.1679. Min Act: -0.1700

Data Index: 1227958 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 3.6229. Min Range: -3.6229

Max Act: 3.1522. Min Act: -0.1700

Data Index: 261904 (C4 (Web Text))

Max Activating Token Index: 515

Text #14

Max Range: 3.6229. Min Range: -3.6229

Max Act: 3.1364. Min Act: -0.1700

Data Index: 1175777 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 3.6229. Min Range: -3.6229

Max Act: 3.1522. Min Act: -0.1700

Data Index: 572152 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 3.6229. Min Range: -3.6229

Max Act: 3.1522. Min Act: -0.1700

Data Index: 1330393 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 3.6229. Min Range: -3.6229

Max Act: 3.1364. Min Act: -0.1700

Data Index: 792509 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 3.6229. Min Range: -3.6229

Max Act: 3.1364. Min Act: -0.1700

Data Index: 864020 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 3.6229. Min Range: -3.6229

Max Act: 3.1207. Min Act: -0.1700

Data Index: 460849 (C4 (Web Text))

Max Activating Token Index: 81