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

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

Neuron 45 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.3096. Min Act: -0.1700

Data Index: 1152049 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.1209. Min Act: -0.1700

Data Index: 520690 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.1209. Min Act: -0.1700

Data Index: 154695 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.0893. Min Act: -0.1700

Data Index: 329908 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.0736. Min Act: -0.1700

Data Index: 508408 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.0736. Min Act: -0.1700

Data Index: 629935 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.0893. Min Act: -0.1700

Data Index: 400110 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.0893. Min Act: -0.1700

Data Index: 1335891 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.0736. Min Act: -0.1700

Data Index: 774269 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.0736. Min Act: -0.1700

Data Index: 744226 (C4 (Web Text))

Max Activating Token Index: 238

Text #10

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.0736. Min Act: -0.1700

Data Index: 932306 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.0420. Min Act: -0.1700

Data Index: 644805 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.0420. Min Act: -0.1700

Data Index: 7967 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.0578. Min Act: -0.1700

Data Index: 1011800 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.0104. Min Act: -0.1700

Data Index: 1185375 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.0420. Min Act: -0.1700

Data Index: 942325 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.0262. Min Act: -0.1700

Data Index: 59169 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.0262. Min Act: -0.1700

Data Index: 173643 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.0262. Min Act: -0.1700

Data Index: 553881 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 3.3096. Min Range: -3.3096

Max Act: 3.0262. Min Act: -0.1700

Data Index: 181379 (C4 (Web Text))

Max Activating Token Index: 749