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

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

Neuron 744 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: 5.6683. Min Range: -5.6683

Max Act: 5.6683. Min Act: -0.1700

Data Index: 1100985 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.6683. Min Act: -0.1700

Data Index: 588473 (C4 (Web Text))

Max Activating Token Index: 686

Text #2

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.5433. Min Act: -0.1700

Data Index: 1167090 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.4495. Min Act: -0.1700

Data Index: 523299 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.4808. Min Act: -0.1700

Data Index: 131463 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.4495. Min Act: -0.1700

Data Index: 39711 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.3558. Min Act: -0.1700

Data Index: 557587 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.4808. Min Act: -0.1700

Data Index: 1270889 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.4183. Min Act: -0.1700

Data Index: 609551 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.4183. Min Act: -0.1700

Data Index: 976719 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.3870. Min Act: -0.1700

Data Index: 634924 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.4495. Min Act: -0.1700

Data Index: 347385 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.3870. Min Act: -0.1700

Data Index: 63531 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.3870. Min Act: -0.1700

Data Index: 110917 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.3870. Min Act: -0.1700

Data Index: 543318 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.3870. Min Act: -0.1700

Data Index: 531868 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.3558. Min Act: -0.1700

Data Index: 1188952 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.2620. Min Act: -0.1700

Data Index: 92535 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.3245. Min Act: -0.1700

Data Index: 112898 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 5.6683. Min Range: -5.6683

Max Act: 5.3870. Min Act: -0.1700

Data Index: 1328258 (C4 (Web Text))

Max Activating Token Index: 751