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

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

Neuron 464 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: 5.3323. Min Range: -5.3323

Max Act: 5.3323. Min Act: -0.1700

Data Index: 608759 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 5.3323. Min Range: -5.3323

Max Act: 5.2073. Min Act: -0.1700

Data Index: 531168 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 5.3323. Min Range: -5.3323

Max Act: 5.2386. Min Act: -0.1700

Data Index: 241162 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 5.3323. Min Range: -5.3323

Max Act: 5.2698. Min Act: -0.1700

Data Index: 374922 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 5.3323. Min Range: -5.3323

Max Act: 5.1761. Min Act: -0.1700

Data Index: 1133222 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 5.3323. Min Range: -5.3323

Max Act: 5.1136. Min Act: -0.1700

Data Index: 170633 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 5.3323. Min Range: -5.3323

Max Act: 5.0511. Min Act: -0.1700

Data Index: 814794 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 5.3323. Min Range: -5.3323

Max Act: 5.0511. Min Act: -0.1700

Data Index: 1035667 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 5.3323. Min Range: -5.3323

Max Act: 5.0198. Min Act: -0.1700

Data Index: 226507 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 5.3323. Min Range: -5.3323

Max Act: 5.0511. Min Act: -0.1700

Data Index: 174595 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 5.3323. Min Range: -5.3323

Max Act: 4.9886. Min Act: -0.1700

Data Index: 1030434 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 5.3323. Min Range: -5.3323

Max Act: 5.0198. Min Act: -0.1700

Data Index: 320282 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 5.3323. Min Range: -5.3323

Max Act: 5.0198. Min Act: -0.1700

Data Index: 132557 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 5.3323. Min Range: -5.3323

Max Act: 4.9573. Min Act: -0.1700

Data Index: 880594 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 5.3323. Min Range: -5.3323

Max Act: 4.9573. Min Act: -0.1700

Data Index: 1270698 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 5.3323. Min Range: -5.3323

Max Act: 4.9573. Min Act: -0.1700

Data Index: 642910 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 5.3323. Min Range: -5.3323

Max Act: 4.8948. Min Act: -0.1700

Data Index: 661005 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 5.3323. Min Range: -5.3323

Max Act: 4.9573. Min Act: -0.1700

Data Index: 53886 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 5.3323. Min Range: -5.3323

Max Act: 4.8948. Min Act: -0.1700

Data Index: 544886 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 5.3323. Min Range: -5.3323

Max Act: 4.9261. Min Act: -0.1700

Data Index: 596143 (C4 (Web Text))

Max Activating Token Index: 969