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

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

Neuron 155 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: 3.9040. Min Range: -3.9040

Max Act: 3.8884. Min Act: -0.1700

Data Index: 1357017 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 3.9040. Min Range: -3.9040

Max Act: 3.8884. Min Act: -0.1700

Data Index: 39597 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 3.9040. Min Range: -3.9040

Max Act: 3.9040. Min Act: -0.1700

Data Index: 1097983 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 3.9040. Min Range: -3.9040

Max Act: 3.7476. Min Act: -0.1700

Data Index: 423138 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 3.9040. Min Range: -3.9040

Max Act: 3.8571. Min Act: -0.1700

Data Index: 589769 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 3.9040. Min Range: -3.9040

Max Act: 3.8258. Min Act: -0.1700

Data Index: 1019692 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 3.9040. Min Range: -3.9040

Max Act: 3.7945. Min Act: -0.1700

Data Index: 1184196 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 3.9040. Min Range: -3.9040

Max Act: 3.7632. Min Act: -0.1700

Data Index: 202682 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 3.9040. Min Range: -3.9040

Max Act: 3.7789. Min Act: -0.1700

Data Index: 165515 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 3.9040. Min Range: -3.9040

Max Act: 3.7632. Min Act: -0.1700

Data Index: 109018 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 3.9040. Min Range: -3.9040

Max Act: 3.8102. Min Act: -0.1700

Data Index: 378700 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 3.9040. Min Range: -3.9040

Max Act: 3.7476. Min Act: -0.1700

Data Index: 846219 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 3.9040. Min Range: -3.9040

Max Act: 3.7007. Min Act: -0.1700

Data Index: 230738 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 3.9040. Min Range: -3.9040

Max Act: 3.7789. Min Act: -0.1700

Data Index: 752426 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 3.9040. Min Range: -3.9040

Max Act: 3.7163. Min Act: -0.1700

Data Index: 560982 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 3.9040. Min Range: -3.9040

Max Act: 3.7163. Min Act: -0.1700

Data Index: 381922 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 3.9040. Min Range: -3.9040

Max Act: 3.7320. Min Act: -0.1700

Data Index: 424717 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 3.9040. Min Range: -3.9040

Max Act: 3.6850. Min Act: -0.1700

Data Index: 158794 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 3.9040. Min Range: -3.9040

Max Act: 3.7163. Min Act: -0.1700

Data Index: 317104 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 3.9040. Min Range: -3.9040

Max Act: 3.7789. Min Act: -0.1700

Data Index: 793114 (C4 (Web Text))

Max Activating Token Index: 686