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

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

Neuron 1665 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: 3.9095. Min Range: -3.9095

Max Act: 3.9095. Min Act: -0.1700

Data Index: 430284 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 3.9095. Min Range: -3.9095

Max Act: 3.8470. Min Act: -0.1700

Data Index: 1159914 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 3.9095. Min Range: -3.9095

Max Act: 3.8157. Min Act: -0.1700

Data Index: 507092 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 3.9095. Min Range: -3.9095

Max Act: 3.7531. Min Act: -0.1700

Data Index: 989695 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 3.9095. Min Range: -3.9095

Max Act: 3.6905. Min Act: -0.1700

Data Index: 1263802 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 3.9095. Min Range: -3.9095

Max Act: 3.6905. Min Act: -0.1700

Data Index: 317815 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.9095. Min Range: -3.9095

Max Act: 3.7218. Min Act: -0.1700

Data Index: 626899 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 3.9095. Min Range: -3.9095

Max Act: 3.7218. Min Act: -0.1700

Data Index: 217064 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 3.9095. Min Range: -3.9095

Max Act: 3.6905. Min Act: -0.1700

Data Index: 1314944 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 3.9095. Min Range: -3.9095

Max Act: 3.7531. Min Act: -0.1700

Data Index: 576496 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 3.9095. Min Range: -3.9095

Max Act: 3.7218. Min Act: -0.1700

Data Index: 276041 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 3.9095. Min Range: -3.9095

Max Act: 3.6592. Min Act: -0.1700

Data Index: 614661 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 3.9095. Min Range: -3.9095

Max Act: 3.6905. Min Act: -0.1700

Data Index: 496266 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 3.9095. Min Range: -3.9095

Max Act: 3.6279. Min Act: -0.1700

Data Index: 434595 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 3.9095. Min Range: -3.9095

Max Act: 3.6905. Min Act: -0.1700

Data Index: 1127280 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 3.9095. Min Range: -3.9095

Max Act: 3.6592. Min Act: -0.1700

Data Index: 165293 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 3.9095. Min Range: -3.9095

Max Act: 3.6592. Min Act: -0.1700

Data Index: 535870 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 3.9095. Min Range: -3.9095

Max Act: 3.6592. Min Act: -0.1700

Data Index: 164774 (C4 (Web Text))

Max Activating Token Index: 547

Text #18

Max Range: 3.9095. Min Range: -3.9095

Max Act: 3.6905. Min Act: -0.1700

Data Index: 1172732 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 3.9095. Min Range: -3.9095

Max Act: 3.6592. Min Act: -0.1700

Data Index: 327942 (C4 (Web Text))

Max Activating Token Index: 665