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

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

Neuron 369 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: 3.3968. Min Range: -3.3968

Max Act: 3.3968. Min Act: -0.1700

Data Index: 882604 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.3026. Min Act: -0.1700

Data Index: 454353 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.3340. Min Act: -0.1700

Data Index: 172902 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2240. Min Act: -0.1700

Data Index: 451559 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2083. Min Act: -0.1700

Data Index: 606777 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.1611. Min Act: -0.1700

Data Index: 718240 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.1296. Min Act: -0.1700

Data Index: 391951 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.0981. Min Act: -0.1700

Data Index: 387856 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.1453. Min Act: -0.1700

Data Index: 26283 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.1138. Min Act: -0.1700

Data Index: 868899 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.0823. Min Act: -0.1700

Data Index: 1332392 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.1453. Min Act: -0.1700

Data Index: 1054469 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.1296. Min Act: -0.1700

Data Index: 1122065 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.1611. Min Act: -0.1700

Data Index: 1014796 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.0823. Min Act: -0.1700

Data Index: 1019952 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.0981. Min Act: -0.1700

Data Index: 108557 (C4 (Web Text))

Max Activating Token Index: 723

Text #16

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.0823. Min Act: -0.1700

Data Index: 832902 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.0665. Min Act: -0.1700

Data Index: 798182 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.0665. Min Act: -0.1700

Data Index: 369616 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 3.3968. Min Range: -3.3968

Max Act: 2.9875. Min Act: -0.1700

Data Index: 229877 (C4 (Web Text))

Max Activating Token Index: 654