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

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

Neuron 796 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: 6.2248. Min Range: -6.2248

Max Act: 6.2248. Min Act: -0.1700

Data Index: 918508 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 6.2248. Min Range: -6.2248

Max Act: 6.0998. Min Act: -0.1700

Data Index: 1148318 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 6.2248. Min Range: -6.2248

Max Act: 6.1623. Min Act: -0.1700

Data Index: 1216183 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 6.2248. Min Range: -6.2248

Max Act: 6.0998. Min Act: -0.1700

Data Index: 539739 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 6.2248. Min Range: -6.2248

Max Act: 6.0686. Min Act: -0.1700

Data Index: 1038470 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 6.2248. Min Range: -6.2248

Max Act: 6.0998. Min Act: -0.1700

Data Index: 708116 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 6.2248. Min Range: -6.2248

Max Act: 6.0686. Min Act: -0.1700

Data Index: 901566 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 6.2248. Min Range: -6.2248

Max Act: 5.9748. Min Act: -0.1700

Data Index: 574285 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 6.2248. Min Range: -6.2248

Max Act: 5.9748. Min Act: -0.1700

Data Index: 455636 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 6.2248. Min Range: -6.2248

Max Act: 6.0061. Min Act: -0.1699

Data Index: 1359244 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 6.2248. Min Range: -6.2248

Max Act: 5.9436. Min Act: -0.1700

Data Index: 1254784 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 6.2248. Min Range: -6.2248

Max Act: 5.9748. Min Act: -0.1700

Data Index: 1167902 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 6.2248. Min Range: -6.2248

Max Act: 5.9123. Min Act: -0.1700

Data Index: 532163 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 6.2248. Min Range: -6.2248

Max Act: 5.9123. Min Act: -0.1700

Data Index: 984481 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 6.2248. Min Range: -6.2248

Max Act: 5.9123. Min Act: -0.1700

Data Index: 975455 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 6.2248. Min Range: -6.2248

Max Act: 5.8811. Min Act: -0.1700

Data Index: 1334087 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 6.2248. Min Range: -6.2248

Max Act: 5.8811. Min Act: -0.1699

Data Index: 871873 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 6.2248. Min Range: -6.2248

Max Act: 5.8498. Min Act: -0.1700

Data Index: 1317490 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 6.2248. Min Range: -6.2248

Max Act: 5.9123. Min Act: -0.1700

Data Index: 839383 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 6.2248. Min Range: -6.2248

Max Act: 5.8811. Min Act: -0.1700

Data Index: 773704 (C4 (Web Text))

Max Activating Token Index: 1023