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

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

Neuron 918 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.7254. Min Act: -0.1700

Data Index: 318518 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.3808. Min Act: -0.1700

Data Index: 368826 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.3180. Min Act: -0.1700

Data Index: 113483 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.3180. Min Act: -0.1700

Data Index: 368016 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.3180. Min Act: -0.1700

Data Index: 1538326 (Python Code)

Max Activating Token Index: 629

Text #5

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.2866. Min Act: -0.1700

Data Index: 458645 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.3023. Min Act: -0.1700

Data Index: 174452 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.3180. Min Act: -0.1700

Data Index: 975352 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.2866. Min Act: -0.1700

Data Index: 169653 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.3023. Min Act: -0.1700

Data Index: 1254442 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.3337. Min Act: -0.1700

Data Index: 285721 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.3023. Min Act: -0.1700

Data Index: 1302076 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.2866. Min Act: -0.1700

Data Index: 795193 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.2238. Min Act: -0.1700

Data Index: 36011 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.2552. Min Act: -0.1700

Data Index: 1628045 (Python Code)

Max Activating Token Index: 122

Text #15

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.2552. Min Act: -0.1700

Data Index: 1089253 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.2395. Min Act: -0.1700

Data Index: 429619 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.2709. Min Act: -0.1700

Data Index: 705854 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.2395. Min Act: -0.1700

Data Index: 157415 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 3.7254. Min Range: -3.7254

Max Act: 3.2552. Min Act: -0.1700

Data Index: 498198 (C4 (Web Text))

Max Activating Token Index: 612