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

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

Neuron 1335 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.6521. Min Range: -5.6521

Max Act: 5.6521. Min Act: -0.1700

Data Index: 604410 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 5.6521. Min Range: -5.6521

Max Act: 5.4021. Min Act: -0.1700

Data Index: 572059 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 5.6521. Min Range: -5.6521

Max Act: 5.4021. Min Act: -0.1700

Data Index: 950008 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 5.6521. Min Range: -5.6521

Max Act: 5.2771. Min Act: -0.1700

Data Index: 674877 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 5.6521. Min Range: -5.6521

Max Act: 5.2771. Min Act: -0.1700

Data Index: 867787 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 5.6521. Min Range: -5.6521

Max Act: 5.3083. Min Act: -0.1700

Data Index: 1233884 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 5.6521. Min Range: -5.6521

Max Act: 5.3083. Min Act: -0.1700

Data Index: 1038087 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 5.6521. Min Range: -5.6521

Max Act: 5.3083. Min Act: -0.1700

Data Index: 759175 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 5.6521. Min Range: -5.6521

Max Act: 5.2771. Min Act: -0.1700

Data Index: 1080236 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 5.6521. Min Range: -5.6521

Max Act: 5.3083. Min Act: -0.1700

Data Index: 871626 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 5.6521. Min Range: -5.6521

Max Act: 5.2771. Min Act: -0.1700

Data Index: 335485 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 5.6521. Min Range: -5.6521

Max Act: 5.2146. Min Act: -0.1700

Data Index: 720485 (C4 (Web Text))

Max Activating Token Index: 484

Text #12

Max Range: 5.6521. Min Range: -5.6521

Max Act: 5.2146. Min Act: -0.1700

Data Index: 1304183 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 5.6521. Min Range: -5.6521

Max Act: 5.2146. Min Act: -0.1700

Data Index: 360452 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 5.6521. Min Range: -5.6521

Max Act: 5.2458. Min Act: -0.1700

Data Index: 1252045 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 5.6521. Min Range: -5.6521

Max Act: 5.2146. Min Act: -0.1700

Data Index: 825296 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 5.6521. Min Range: -5.6521

Max Act: 5.1833. Min Act: -0.1700

Data Index: 1075107 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 5.6521. Min Range: -5.6521

Max Act: 5.1521. Min Act: -0.1700

Data Index: 866539 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 5.6521. Min Range: -5.6521

Max Act: 5.1833. Min Act: -0.1700

Data Index: 917571 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 5.6521. Min Range: -5.6521

Max Act: 5.1521. Min Act: -0.1700

Data Index: 124119 (C4 (Web Text))

Max Activating Token Index: 204