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

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

Neuron 1629 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: 5.4164. Min Range: -5.4164

Max Act: 5.4164. Min Act: -0.1700

Data Index: 104066 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 5.4164. Min Range: -5.4164

Max Act: 5.4164. Min Act: -0.1700

Data Index: 843140 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 5.4164. Min Range: -5.4164

Max Act: 5.3539. Min Act: -0.1700

Data Index: 316554 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 5.4164. Min Range: -5.4164

Max Act: 5.3539. Min Act: -0.1700

Data Index: 1147726 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 5.4164. Min Range: -5.4164

Max Act: 5.3539. Min Act: -0.1700

Data Index: 790434 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 5.4164. Min Range: -5.4164

Max Act: 5.2914. Min Act: -0.1700

Data Index: 1223485 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 5.4164. Min Range: -5.4164

Max Act: 5.3227. Min Act: -0.1700

Data Index: 1094875 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 5.4164. Min Range: -5.4164

Max Act: 5.2914. Min Act: -0.1700

Data Index: 487301 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 5.4164. Min Range: -5.4164

Max Act: 5.2914. Min Act: -0.1700

Data Index: 1293848 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 5.4164. Min Range: -5.4164

Max Act: 5.2914. Min Act: -0.1700

Data Index: 924373 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 5.4164. Min Range: -5.4164

Max Act: 5.2289. Min Act: -0.1700

Data Index: 457837 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 5.4164. Min Range: -5.4164

Max Act: 5.2289. Min Act: -0.1700

Data Index: 1077719 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 5.4164. Min Range: -5.4164

Max Act: 5.1977. Min Act: -0.1700

Data Index: 965043 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 5.4164. Min Range: -5.4164

Max Act: 5.1039. Min Act: -0.1700

Data Index: 592820 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 5.4164. Min Range: -5.4164

Max Act: 5.1664. Min Act: -0.1700

Data Index: 1078441 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 5.4164. Min Range: -5.4164

Max Act: 5.1039. Min Act: -0.1700

Data Index: 349694 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 5.4164. Min Range: -5.4164

Max Act: 5.1352. Min Act: -0.1700

Data Index: 524308 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 5.4164. Min Range: -5.4164

Max Act: 5.1352. Min Act: -0.1700

Data Index: 1103930 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 5.4164. Min Range: -5.4164

Max Act: 5.1977. Min Act: -0.1700

Data Index: 9039 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 5.4164. Min Range: -5.4164

Max Act: 5.1039. Min Act: -0.1700

Data Index: 428797 (C4 (Web Text))

Max Activating Token Index: 828