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

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

Neuron 1982 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: 5.4793. Min Range: -5.4793

Max Act: 5.4793. Min Act: -0.1700

Data Index: 638335 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 5.4793. Min Range: -5.4793

Max Act: 5.0418. Min Act: -0.1700

Data Index: 1216940 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 5.4793. Min Range: -5.4793

Max Act: 5.0730. Min Act: -0.1699

Data Index: 203562 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 5.4793. Min Range: -5.4793

Max Act: 5.0418. Min Act: -0.1700

Data Index: 897722 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 5.4793. Min Range: -5.4793

Max Act: 5.0730. Min Act: -0.1700

Data Index: 945617 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 5.4793. Min Range: -5.4793

Max Act: 4.9793. Min Act: -0.1700

Data Index: 215211 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 5.4793. Min Range: -5.4793

Max Act: 4.9793. Min Act: -0.1700

Data Index: 497436 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 5.4793. Min Range: -5.4793

Max Act: 4.9793. Min Act: -0.1700

Data Index: 387199 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 5.4793. Min Range: -5.4793

Max Act: 4.9793. Min Act: -0.1700

Data Index: 857059 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 5.4793. Min Range: -5.4793

Max Act: 5.0105. Min Act: -0.1700

Data Index: 140221 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 5.4793. Min Range: -5.4793

Max Act: 4.9480. Min Act: -0.1700

Data Index: 877062 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 5.4793. Min Range: -5.4793

Max Act: 4.9480. Min Act: -0.1700

Data Index: 810031 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 5.4793. Min Range: -5.4793

Max Act: 4.9480. Min Act: -0.1700

Data Index: 1026320 (C4 (Web Text))

Max Activating Token Index: 356

Text #13

Max Range: 5.4793. Min Range: -5.4793

Max Act: 4.9168. Min Act: -0.1700

Data Index: 61466 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 5.4793. Min Range: -5.4793

Max Act: 4.9480. Min Act: -0.1700

Data Index: 356298 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 5.4793. Min Range: -5.4793

Max Act: 4.8855. Min Act: -0.1700

Data Index: 4170 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 5.4793. Min Range: -5.4793

Max Act: 4.8855. Min Act: -0.1700

Data Index: 150239 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 5.4793. Min Range: -5.4793

Max Act: 4.9168. Min Act: -0.1700

Data Index: 1198033 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 5.4793. Min Range: -5.4793

Max Act: 4.8855. Min Act: -0.1700

Data Index: 206559 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 5.4793. Min Range: -5.4793

Max Act: 4.9168. Min Act: -0.1700

Data Index: 751016 (C4 (Web Text))

Max Activating Token Index: 445