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

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

Neuron 105 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9372. Min Range: -3.9372

Max Act: 3.9372. Min Act: -0.1700

Data Index: 288198 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 3.9372. Min Range: -3.9372

Max Act: 3.8433. Min Act: -0.1700

Data Index: 38437 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 3.9372. Min Range: -3.9372

Max Act: 3.9059. Min Act: -0.1700

Data Index: 1099714 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 3.9372. Min Range: -3.9372

Max Act: 3.7182. Min Act: -0.1700

Data Index: 1046956 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 3.9372. Min Range: -3.9372

Max Act: 3.8433. Min Act: -0.1700

Data Index: 1033438 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 3.9372. Min Range: -3.9372

Max Act: 3.8433. Min Act: -0.1700

Data Index: 920415 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 3.9372. Min Range: -3.9372

Max Act: 3.7808. Min Act: -0.1700

Data Index: 945141 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 3.9372. Min Range: -3.9372

Max Act: 3.7495. Min Act: -0.1700

Data Index: 971083 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 3.9372. Min Range: -3.9372

Max Act: 3.7182. Min Act: -0.1700

Data Index: 689517 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 3.9372. Min Range: -3.9372

Max Act: 3.7182. Min Act: -0.1700

Data Index: 248175 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 3.9372. Min Range: -3.9372

Max Act: 3.6869. Min Act: -0.1700

Data Index: 697967 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 3.9372. Min Range: -3.9372

Max Act: 3.7495. Min Act: -0.1700

Data Index: 496475 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 3.9372. Min Range: -3.9372

Max Act: 3.6869. Min Act: -0.1700

Data Index: 509993 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 3.9372. Min Range: -3.9372

Max Act: 3.6556. Min Act: -0.1700

Data Index: 824314 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 3.9372. Min Range: -3.9372

Max Act: 3.7182. Min Act: -0.1700

Data Index: 1055319 (C4 (Web Text))

Max Activating Token Index: 547

Text #15

Max Range: 3.9372. Min Range: -3.9372

Max Act: 3.7182. Min Act: -0.1700

Data Index: 845370 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 3.9372. Min Range: -3.9372

Max Act: 3.6556. Min Act: -0.1700

Data Index: 133645 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 3.9372. Min Range: -3.9372

Max Act: 3.6869. Min Act: -0.1700

Data Index: 815082 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 3.9372. Min Range: -3.9372

Max Act: 3.6243. Min Act: -0.1700

Data Index: 132123 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 3.9372. Min Range: -3.9372

Max Act: 3.5930. Min Act: -0.1700

Data Index: 105281 (C4 (Web Text))

Max Activating Token Index: 684