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

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

Neuron 295 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: 3.5696. Min Range: -3.5696

Max Act: 3.5696. Min Act: -0.1700

Data Index: 940335 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 3.5696. Min Range: -3.5696

Max Act: 3.5383. Min Act: -0.1700

Data Index: 1127949 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 3.5696. Min Range: -3.5696

Max Act: 3.5069. Min Act: -0.1700

Data Index: 1153824 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 3.5696. Min Range: -3.5696

Max Act: 3.5226. Min Act: -0.1700

Data Index: 1319479 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 3.5696. Min Range: -3.5696

Max Act: 3.5226. Min Act: -0.1700

Data Index: 513106 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 3.5696. Min Range: -3.5696

Max Act: 3.5069. Min Act: -0.1700

Data Index: 990389 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 3.5696. Min Range: -3.5696

Max Act: 3.4599. Min Act: -0.1700

Data Index: 19980 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 3.5696. Min Range: -3.5696

Max Act: 3.4756. Min Act: -0.1700

Data Index: 868698 (C4 (Web Text))

Max Activating Token Index: 486

Text #8

Max Range: 3.5696. Min Range: -3.5696

Max Act: 3.4756. Min Act: -0.1700

Data Index: 22519 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 3.5696. Min Range: -3.5696

Max Act: 3.4756. Min Act: -0.1700

Data Index: 1305091 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 3.5696. Min Range: -3.5696

Max Act: 3.4599. Min Act: -0.1700

Data Index: 32744 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 3.5696. Min Range: -3.5696

Max Act: 3.4599. Min Act: -0.1700

Data Index: 877455 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 3.5696. Min Range: -3.5696

Max Act: 3.4442. Min Act: -0.1700

Data Index: 956832 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 3.5696. Min Range: -3.5696

Max Act: 3.4599. Min Act: -0.1700

Data Index: 923358 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 3.5696. Min Range: -3.5696

Max Act: 3.4442. Min Act: -0.1700

Data Index: 1074726 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 3.5696. Min Range: -3.5696

Max Act: 3.4442. Min Act: -0.1700

Data Index: 691041 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 3.5696. Min Range: -3.5696

Max Act: 3.4599. Min Act: -0.1700

Data Index: 660453 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 3.5696. Min Range: -3.5696

Max Act: 3.4442. Min Act: -0.1700

Data Index: 190339 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 3.5696. Min Range: -3.5696

Max Act: 3.4442. Min Act: -0.1700

Data Index: 143467 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 3.5696. Min Range: -3.5696

Max Act: 3.4442. Min Act: -0.1700

Data Index: 712562 (C4 (Web Text))

Max Activating Token Index: 288