Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 722 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.9602. Min Range: -5.9602

Max Act: 5.9602. Min Act: -0.1700

Data Index: 904049 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 5.9602. Min Range: -5.9602

Max Act: 5.9289. Min Act: -0.1700

Data Index: 798940 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 5.9602. Min Range: -5.9602

Max Act: 5.8664. Min Act: -0.1700

Data Index: 766103 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 5.9602. Min Range: -5.9602

Max Act: 5.8352. Min Act: -0.1700

Data Index: 1282688 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 5.9602. Min Range: -5.9602

Max Act: 5.6789. Min Act: -0.1700

Data Index: 258899 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 5.9602. Min Range: -5.9602

Max Act: 5.7727. Min Act: -0.1700

Data Index: 569864 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 5.9602. Min Range: -5.9602

Max Act: 5.5852. Min Act: -0.1700

Data Index: 1043338 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 5.9602. Min Range: -5.9602

Max Act: 5.6164. Min Act: -0.1700

Data Index: 87312 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 5.9602. Min Range: -5.9602

Max Act: 5.5539. Min Act: -0.1700

Data Index: 741868 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 5.9602. Min Range: -5.9602

Max Act: 5.5852. Min Act: -0.1700

Data Index: 1262015 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 5.9602. Min Range: -5.9602

Max Act: 5.6789. Min Act: -0.1700

Data Index: 845575 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 5.9602. Min Range: -5.9602

Max Act: 5.5227. Min Act: -0.1700

Data Index: 400051 (C4 (Web Text))

Max Activating Token Index: 583

Text #12

Max Range: 5.9602. Min Range: -5.9602

Max Act: 5.3352. Min Act: -0.1700

Data Index: 964406 (C4 (Web Text))

Max Activating Token Index: 881

Text #13

Max Range: 5.9602. Min Range: -5.9602

Max Act: 5.7414. Min Act: -0.1700

Data Index: 462127 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 5.9602. Min Range: -5.9602

Max Act: 5.6164. Min Act: -0.1699

Data Index: 619314 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 5.9602. Min Range: -5.9602

Max Act: 5.7102. Min Act: -0.1700

Data Index: 326540 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 5.9602. Min Range: -5.9602

Max Act: 5.6789. Min Act: -0.1700

Data Index: 855757 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 5.9602. Min Range: -5.9602

Max Act: 5.6164. Min Act: -0.1700

Data Index: 916135 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 5.9602. Min Range: -5.9602

Max Act: 5.5227. Min Act: -0.1700

Data Index: 845562 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 5.9602. Min Range: -5.9602

Max Act: 5.3977. Min Act: -0.1700

Data Index: 444460 (C4 (Web Text))

Max Activating Token Index: 961