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

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

Neuron 1888 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: 3.3009. Min Range: -3.3009

Max Act: 3.3009. Min Act: -0.1700

Data Index: 191614 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 3.3009. Min Range: -3.3009

Max Act: 3.2852. Min Act: -0.1700

Data Index: 641918 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 3.3009. Min Range: -3.3009

Max Act: 3.2695. Min Act: -0.1700

Data Index: 1259744 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 3.3009. Min Range: -3.3009

Max Act: 3.2852. Min Act: -0.1700

Data Index: 1315187 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 3.3009. Min Range: -3.3009

Max Act: 3.2223. Min Act: -0.1700

Data Index: 477156 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 3.3009. Min Range: -3.3009

Max Act: 3.2223. Min Act: -0.1700

Data Index: 849946 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 3.3009. Min Range: -3.3009

Max Act: 3.1751. Min Act: -0.1700

Data Index: 63004 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 3.3009. Min Range: -3.3009

Max Act: 3.1751. Min Act: -0.1700

Data Index: 302482 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 3.3009. Min Range: -3.3009

Max Act: 3.1908. Min Act: -0.1700

Data Index: 1277468 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 3.3009. Min Range: -3.3009

Max Act: 3.1751. Min Act: -0.1700

Data Index: 48091 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 3.3009. Min Range: -3.3009

Max Act: 3.2066. Min Act: -0.1700

Data Index: 743854 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 3.3009. Min Range: -3.3009

Max Act: 3.2223. Min Act: -0.1700

Data Index: 555253 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 3.3009. Min Range: -3.3009

Max Act: 3.1751. Min Act: -0.1700

Data Index: 584931 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 3.3009. Min Range: -3.3009

Max Act: 3.1908. Min Act: -0.1700

Data Index: 218396 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 3.3009. Min Range: -3.3009

Max Act: 3.1908. Min Act: -0.1700

Data Index: 87907 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 3.3009. Min Range: -3.3009

Max Act: 3.1594. Min Act: -0.1700

Data Index: 255444 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 3.3009. Min Range: -3.3009

Max Act: 3.1594. Min Act: -0.1700

Data Index: 1348146 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 3.3009. Min Range: -3.3009

Max Act: 3.1751. Min Act: -0.1700

Data Index: 1270256 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 3.3009. Min Range: -3.3009

Max Act: 3.1279. Min Act: -0.1700

Data Index: 120083 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 3.3009. Min Range: -3.3009

Max Act: 3.1279. Min Act: -0.1699

Data Index: 613538 (C4 (Web Text))

Max Activating Token Index: 65