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

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

Neuron 1894 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: 5.9966. Min Range: -5.9966

Max Act: 5.9966. Min Act: -0.1700

Data Index: 1303783 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 5.9966. Min Range: -5.9966

Max Act: 5.8091. Min Act: -0.1700

Data Index: 972505 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 5.9966. Min Range: -5.9966

Max Act: 5.6841. Min Act: -0.1700

Data Index: 970558 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 5.9966. Min Range: -5.9966

Max Act: 5.6841. Min Act: -0.1700

Data Index: 1104579 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 5.9966. Min Range: -5.9966

Max Act: 5.6216. Min Act: -0.1700

Data Index: 1119541 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 5.9966. Min Range: -5.9966

Max Act: 5.6528. Min Act: -0.1700

Data Index: 292023 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 5.9966. Min Range: -5.9966

Max Act: 5.5278. Min Act: -0.1700

Data Index: 449120 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 5.9966. Min Range: -5.9966

Max Act: 5.6216. Min Act: -0.1700

Data Index: 1167413 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 5.9966. Min Range: -5.9966

Max Act: 5.5591. Min Act: -0.1700

Data Index: 991971 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 5.9966. Min Range: -5.9966

Max Act: 5.5903. Min Act: -0.1700

Data Index: 339306 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 5.9966. Min Range: -5.9966

Max Act: 5.5278. Min Act: -0.1700

Data Index: 261871 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 5.9966. Min Range: -5.9966

Max Act: 5.4966. Min Act: -0.1700

Data Index: 439900 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 5.9966. Min Range: -5.9966

Max Act: 5.4966. Min Act: -0.1700

Data Index: 1328796 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 5.9966. Min Range: -5.9966

Max Act: 5.4341. Min Act: -0.1700

Data Index: 1233031 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 5.9966. Min Range: -5.9966

Max Act: 5.4966. Min Act: -0.1700

Data Index: 84401 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 5.9966. Min Range: -5.9966

Max Act: 5.4341. Min Act: -0.1700

Data Index: 724830 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 5.9966. Min Range: -5.9966

Max Act: 5.4653. Min Act: -0.1700

Data Index: 1016009 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 5.9966. Min Range: -5.9966

Max Act: 5.4028. Min Act: -0.1700

Data Index: 80602 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 5.9966. Min Range: -5.9966

Max Act: 5.4341. Min Act: -0.1700

Data Index: 892408 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 5.9966. Min Range: -5.9966

Max Act: 5.4966. Min Act: -0.1700

Data Index: 712748 (C4 (Web Text))

Max Activating Token Index: 680