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

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

Neuron 301 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.7098. Min Act: -0.1700

Data Index: 1050598 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.6315. Min Act: -0.1700

Data Index: 498399 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.5689. Min Act: -0.1700

Data Index: 1267341 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.5845. Min Act: -0.1700

Data Index: 1260001 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.5532. Min Act: -0.1700

Data Index: 259866 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.5689. Min Act: -0.1700

Data Index: 833131 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.5532. Min Act: -0.1700

Data Index: 46270 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.5376. Min Act: -0.1700

Data Index: 1088681 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.4906. Min Act: -0.1700

Data Index: 943072 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.4906. Min Act: -0.1700

Data Index: 836610 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.4749. Min Act: -0.1700

Data Index: 335795 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.4906. Min Act: -0.1700

Data Index: 1019744 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.4592. Min Act: -0.1700

Data Index: 1168988 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.4435. Min Act: -0.1700

Data Index: 310072 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.4435. Min Act: -0.1700

Data Index: 1145121 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.4122. Min Act: -0.1700

Data Index: 558762 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.4435. Min Act: -0.1700

Data Index: 1062742 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.3965. Min Act: -0.1700

Data Index: 682331 (C4 (Web Text))

Max Activating Token Index: 434

Text #18

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.3965. Min Act: -0.1700

Data Index: 782021 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 3.7098. Min Range: -3.7098

Max Act: 3.3651. Min Act: -0.1700

Data Index: 124652 (C4 (Web Text))

Max Activating Token Index: 985