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

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

Neuron 923 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: 5.5727. Min Range: -5.5727

Max Act: 5.4477. Min Act: -0.1700

Data Index: 22960 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.5727. Min Act: -0.1700

Data Index: 444871 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.4165. Min Act: -0.1700

Data Index: 1356130 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.3540. Min Act: -0.1700

Data Index: 750459 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.3227. Min Act: -0.1700

Data Index: 478564 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.1977. Min Act: -0.1700

Data Index: 672204 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.3227. Min Act: -0.1700

Data Index: 389753 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.3227. Min Act: -0.1700

Data Index: 909540 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.2915. Min Act: -0.1700

Data Index: 202336 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.2602. Min Act: -0.1700

Data Index: 724527 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.3540. Min Act: -0.1700

Data Index: 306523 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.2602. Min Act: -0.1699

Data Index: 764220 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.2915. Min Act: -0.1700

Data Index: 1191802 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.3227. Min Act: -0.1700

Data Index: 903599 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.1977. Min Act: -0.1700

Data Index: 478563 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.2915. Min Act: -0.1700

Data Index: 816660 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.2290. Min Act: -0.1700

Data Index: 458066 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.1352. Min Act: -0.1700

Data Index: 708151 (C4 (Web Text))

Max Activating Token Index: 856

Text #18

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.2290. Min Act: -0.1700

Data Index: 669921 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 5.5727. Min Range: -5.5727

Max Act: 5.1665. Min Act: -0.1700

Data Index: 66083 (C4 (Web Text))

Max Activating Token Index: 874