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

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

Neuron 1388 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6971. Min Range: -5.6971

Max Act: 5.6971. Min Act: -0.1700

Data Index: 664008 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 5.6971. Min Range: -5.6971

Max Act: 5.6658. Min Act: -0.1700

Data Index: 647682 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 5.6971. Min Range: -5.6971

Max Act: 5.5408. Min Act: -0.1700

Data Index: 2818 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 5.6971. Min Range: -5.6971

Max Act: 5.5408. Min Act: -0.1700

Data Index: 988804 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 5.6971. Min Range: -5.6971

Max Act: 5.4783. Min Act: -0.1700

Data Index: 987257 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 5.6971. Min Range: -5.6971

Max Act: 5.4783. Min Act: -0.1700

Data Index: 673313 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 5.6971. Min Range: -5.6971

Max Act: 5.4471. Min Act: -0.1700

Data Index: 1110426 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 5.6971. Min Range: -5.6971

Max Act: 5.4471. Min Act: -0.1700

Data Index: 637336 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 5.6971. Min Range: -5.6971

Max Act: 5.4471. Min Act: -0.1700

Data Index: 42499 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 5.6971. Min Range: -5.6971

Max Act: 5.4158. Min Act: -0.1700

Data Index: 1046282 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 5.6971. Min Range: -5.6971

Max Act: 5.4158. Min Act: -0.1700

Data Index: 459454 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 5.6971. Min Range: -5.6971

Max Act: 5.4158. Min Act: -0.1700

Data Index: 1264579 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 5.6971. Min Range: -5.6971

Max Act: 5.4158. Min Act: -0.1700

Data Index: 518031 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 5.6971. Min Range: -5.6971

Max Act: 5.3846. Min Act: -0.1700

Data Index: 540980 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 5.6971. Min Range: -5.6971

Max Act: 5.3533. Min Act: -0.1700

Data Index: 24788 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 5.6971. Min Range: -5.6971

Max Act: 5.3846. Min Act: -0.1700

Data Index: 1228366 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 5.6971. Min Range: -5.6971

Max Act: 5.3846. Min Act: -0.1700

Data Index: 1308191 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 5.6971. Min Range: -5.6971

Max Act: 5.3221. Min Act: -0.1700

Data Index: 183638 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 5.6971. Min Range: -5.6971

Max Act: 5.3533. Min Act: -0.1700

Data Index: 983256 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 5.6971. Min Range: -5.6971

Max Act: 5.3533. Min Act: -0.1700

Data Index: 961936 (C4 (Web Text))

Max Activating Token Index: 14