Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 803 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 7.8432. Min Range: -7.8432

Max Act: 7.8432. Min Act: -0.1700

Data Index: 1342837 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 7.8432. Min Range: -7.8432

Max Act: 7.7564. Min Act: -0.1699

Data Index: 1356734 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 7.8432. Min Range: -7.8432

Max Act: 7.6752. Min Act: -0.1699

Data Index: 942079 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 7.8432. Min Range: -7.8432

Max Act: 7.7409. Min Act: -0.1699

Data Index: 995225 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 7.8432. Min Range: -7.8432

Max Act: 7.7346. Min Act: -0.1700

Data Index: 1275314 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 7.8432. Min Range: -7.8432

Max Act: 7.7290. Min Act: -0.1700

Data Index: 655582 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 7.8432. Min Range: -7.8432

Max Act: 7.7034. Min Act: -0.1699

Data Index: 515979 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 7.8432. Min Range: -7.8432

Max Act: 7.6799. Min Act: -0.1698

Data Index: 1011709 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 7.8432. Min Range: -7.8432

Max Act: 7.6903. Min Act: -0.1700

Data Index: 695342 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 7.8432. Min Range: -7.8432

Max Act: 7.6927. Min Act: -0.1700

Data Index: 382371 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 7.8432. Min Range: -7.8432

Max Act: 7.6284. Min Act: -0.1700

Data Index: 22339 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 7.8432. Min Range: -7.8432

Max Act: 7.6518. Min Act: -0.1700

Data Index: 1117833 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 7.8432. Min Range: -7.8432

Max Act: 7.5986. Min Act: -0.1698

Data Index: 886894 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 7.8432. Min Range: -7.8432

Max Act: 7.5951. Min Act: -0.1700

Data Index: 986184 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 7.8432. Min Range: -7.8432

Max Act: 7.6153. Min Act: -0.1698

Data Index: 28652 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 7.8432. Min Range: -7.8432

Max Act: 7.6528. Min Act: -0.1700

Data Index: 406142 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 7.8432. Min Range: -7.8432

Max Act: 7.6246. Min Act: -0.1699

Data Index: 87335 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 7.8432. Min Range: -7.8432

Max Act: 7.5735. Min Act: -0.1700

Data Index: 488565 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 7.8432. Min Range: -7.8432

Max Act: 7.4632. Min Act: -0.1700

Data Index: 1195721 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 7.8432. Min Range: -7.8432

Max Act: 7.6092. Min Act: -0.1695

Data Index: 319067 (C4 (Web Text))

Max Activating Token Index: 799