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

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

Neuron 1838 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: 4.1082. Min Range: -4.1082

Max Act: 4.1082. Min Act: -0.1700

Data Index: 202421 (C4 (Web Text))

Max Activating Token Index: 475

Text #1

Max Range: 4.1082. Min Range: -4.1082

Max Act: 4.0770. Min Act: -0.1700

Data Index: 239156 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 4.1082. Min Range: -4.1082

Max Act: 4.0457. Min Act: -0.1700

Data Index: 1217836 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 4.1082. Min Range: -4.1082

Max Act: 4.0457. Min Act: -0.1700

Data Index: 687954 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 4.1082. Min Range: -4.1082

Max Act: 4.0144. Min Act: -0.1700

Data Index: 345062 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 4.1082. Min Range: -4.1082

Max Act: 3.9832. Min Act: -0.1700

Data Index: 828289 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 4.1082. Min Range: -4.1082

Max Act: 3.9519. Min Act: -0.1700

Data Index: 655341 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 4.1082. Min Range: -4.1082

Max Act: 3.9519. Min Act: -0.1700

Data Index: 320532 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 4.1082. Min Range: -4.1082

Max Act: 3.9206. Min Act: -0.1700

Data Index: 654560 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 4.1082. Min Range: -4.1082

Max Act: 3.8894. Min Act: -0.1700

Data Index: 472878 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 4.1082. Min Range: -4.1082

Max Act: 3.9206. Min Act: -0.1700

Data Index: 693420 (C4 (Web Text))

Max Activating Token Index: 259

Text #11

Max Range: 4.1082. Min Range: -4.1082

Max Act: 3.8894. Min Act: -0.1700

Data Index: 1270815 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 4.1082. Min Range: -4.1082

Max Act: 3.9206. Min Act: -0.1700

Data Index: 157073 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 4.1082. Min Range: -4.1082

Max Act: 3.8894. Min Act: -0.1700

Data Index: 1191264 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 4.1082. Min Range: -4.1082

Max Act: 3.8894. Min Act: -0.1700

Data Index: 516957 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 4.1082. Min Range: -4.1082

Max Act: 3.8894. Min Act: -0.1700

Data Index: 871172 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 4.1082. Min Range: -4.1082

Max Act: 3.9206. Min Act: -0.1700

Data Index: 1094476 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 4.1082. Min Range: -4.1082

Max Act: 3.8894. Min Act: -0.1700

Data Index: 1294273 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 4.1082. Min Range: -4.1082

Max Act: 3.9206. Min Act: -0.1700

Data Index: 982343 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 4.1082. Min Range: -4.1082

Max Act: 3.8581. Min Act: -0.1700

Data Index: 605878 (C4 (Web Text))

Max Activating Token Index: 999