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

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

Neuron 187 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: 3.6869. Min Range: -3.6869

Max Act: 3.6869. Min Act: -0.1700

Data Index: 220767 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 3.6869. Min Range: -3.6869

Max Act: 3.6869. Min Act: -0.1700

Data Index: 256369 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 3.6869. Min Range: -3.6869

Max Act: 3.6399. Min Act: -0.1700

Data Index: 549688 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 3.6869. Min Range: -3.6869

Max Act: 3.6399. Min Act: -0.1700

Data Index: 227733 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 3.6869. Min Range: -3.6869

Max Act: 3.6243. Min Act: -0.1700

Data Index: 23398 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 3.6869. Min Range: -3.6869

Max Act: 3.6086. Min Act: -0.1700

Data Index: 405735 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 3.6869. Min Range: -3.6869

Max Act: 3.6086. Min Act: -0.1700

Data Index: 1177737 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 3.6869. Min Range: -3.6869

Max Act: 3.5773. Min Act: -0.1700

Data Index: 47236 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 3.6869. Min Range: -3.6869

Max Act: 3.5460. Min Act: -0.1700

Data Index: 458115 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 3.6869. Min Range: -3.6869

Max Act: 3.5773. Min Act: -0.1700

Data Index: 930336 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 3.6869. Min Range: -3.6869

Max Act: 3.5773. Min Act: -0.1700

Data Index: 527140 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 3.6869. Min Range: -3.6869

Max Act: 3.5146. Min Act: -0.1700

Data Index: 380170 (C4 (Web Text))

Max Activating Token Index: 403

Text #12

Max Range: 3.6869. Min Range: -3.6869

Max Act: 3.6086. Min Act: -0.1700

Data Index: 871815 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 3.6869. Min Range: -3.6869

Max Act: 3.4833. Min Act: -0.1700

Data Index: 481939 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 3.6869. Min Range: -3.6869

Max Act: 3.4990. Min Act: -0.1700

Data Index: 1049400 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 3.6869. Min Range: -3.6869

Max Act: 3.5460. Min Act: -0.1700

Data Index: 215720 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 3.6869. Min Range: -3.6869

Max Act: 3.5616. Min Act: -0.1700

Data Index: 678065 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 3.6869. Min Range: -3.6869

Max Act: 3.6086. Min Act: -0.1700

Data Index: 101073 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 3.6869. Min Range: -3.6869

Max Act: 3.5616. Min Act: -0.1700

Data Index: 1040015 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 3.6869. Min Range: -3.6869

Max Act: 3.2793. Min Act: -0.1700

Data Index: 440648 (C4 (Web Text))

Max Activating Token Index: 87