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

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

Neuron 1304 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: 3.3096. Min Range: -3.3096

Max Act: 3.3096. Min Act: -0.1700

Data Index: 388238 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.3096. Min Act: -0.1700

Data Index: 741316 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.2782. Min Act: -0.1700

Data Index: 597175 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.2782. Min Act: -0.1700

Data Index: 572302 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.2782. Min Act: -0.1700

Data Index: 1303012 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.2310. Min Act: -0.1700

Data Index: 473447 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.2310. Min Act: -0.1700

Data Index: 595716 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.2153. Min Act: -0.1700

Data Index: 820071 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.2310. Min Act: -0.1700

Data Index: 1359514 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.1996. Min Act: -0.1700

Data Index: 878204 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.1996. Min Act: -0.1700

Data Index: 114873 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.2153. Min Act: -0.1700

Data Index: 1115257 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.1996. Min Act: -0.1700

Data Index: 782166 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.1996. Min Act: -0.1700

Data Index: 551771 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.1839. Min Act: -0.1700

Data Index: 493026 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.1839. Min Act: -0.1700

Data Index: 278201 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.1996. Min Act: -0.1700

Data Index: 878232 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.1681. Min Act: -0.1700

Data Index: 11516 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.1839. Min Act: -0.1700

Data Index: 1192794 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.1681. Min Act: -0.1700

Data Index: 713232 (C4 (Web Text))

Max Activating Token Index: 582