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

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

Neuron 1201 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: 5.9801. Min Range: -5.9801

Max Act: 5.9801. Min Act: -0.1700

Data Index: 409554 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 5.9801. Min Range: -5.9801

Max Act: 5.8551. Min Act: -0.1700

Data Index: 883110 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 5.9801. Min Range: -5.9801

Max Act: 5.9176. Min Act: -0.1700

Data Index: 1065685 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 5.9801. Min Range: -5.9801

Max Act: 5.8863. Min Act: -0.1700

Data Index: 10814 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 5.9801. Min Range: -5.9801

Max Act: 5.8238. Min Act: -0.1700

Data Index: 1315653 (C4 (Web Text))

Max Activating Token Index: 512

Text #5

Max Range: 5.9801. Min Range: -5.9801

Max Act: 5.7926. Min Act: -0.1700

Data Index: 114147 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 5.9801. Min Range: -5.9801

Max Act: 5.8551. Min Act: -0.1700

Data Index: 474874 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 5.9801. Min Range: -5.9801

Max Act: 5.7926. Min Act: -0.1700

Data Index: 1123064 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 5.9801. Min Range: -5.9801

Max Act: 5.7613. Min Act: -0.1700

Data Index: 1284304 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 5.9801. Min Range: -5.9801

Max Act: 5.7926. Min Act: -0.1700

Data Index: 236196 (C4 (Web Text))

Max Activating Token Index: 730

Text #10

Max Range: 5.9801. Min Range: -5.9801

Max Act: 5.8238. Min Act: -0.1700

Data Index: 356209 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 5.9801. Min Range: -5.9801

Max Act: 5.7926. Min Act: -0.1700

Data Index: 383127 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 5.9801. Min Range: -5.9801

Max Act: 5.8551. Min Act: -0.1700

Data Index: 530953 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 5.9801. Min Range: -5.9801

Max Act: 5.7613. Min Act: -0.1700

Data Index: 769933 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 5.9801. Min Range: -5.9801

Max Act: 5.7926. Min Act: -0.1700

Data Index: 1336819 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 5.9801. Min Range: -5.9801

Max Act: 5.7301. Min Act: -0.1700

Data Index: 941050 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 5.9801. Min Range: -5.9801

Max Act: 5.8551. Min Act: -0.1700

Data Index: 320361 (C4 (Web Text))

Max Activating Token Index: 724

Text #17

Max Range: 5.9801. Min Range: -5.9801

Max Act: 5.7301. Min Act: -0.1700

Data Index: 1317334 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 5.9801. Min Range: -5.9801

Max Act: 5.7926. Min Act: -0.1700

Data Index: 374132 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 5.9801. Min Range: -5.9801

Max Act: 5.7613. Min Act: -0.1700

Data Index: 746224 (C4 (Web Text))

Max Activating Token Index: 575