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

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

Neuron 1759 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: 5.7145. Min Range: -5.7145

Max Act: 5.7145. Min Act: -0.1700

Data Index: 1233685 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 5.7145. Min Range: -5.7145

Max Act: 5.5270. Min Act: -0.1700

Data Index: 1084370 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 5.7145. Min Range: -5.7145

Max Act: 5.5270. Min Act: -0.1700

Data Index: 666713 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 5.7145. Min Range: -5.7145

Max Act: 5.4645. Min Act: -0.1700

Data Index: 906519 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 5.7145. Min Range: -5.7145

Max Act: 5.4020. Min Act: -0.1700

Data Index: 1200185 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 5.7145. Min Range: -5.7145

Max Act: 5.3708. Min Act: -0.1700

Data Index: 1130608 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 5.7145. Min Range: -5.7145

Max Act: 5.3708. Min Act: -0.1700

Data Index: 971812 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 5.7145. Min Range: -5.7145

Max Act: 5.3708. Min Act: -0.1700

Data Index: 137223 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 5.7145. Min Range: -5.7145

Max Act: 5.3083. Min Act: -0.1700

Data Index: 875650 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 5.7145. Min Range: -5.7145

Max Act: 5.3083. Min Act: -0.1700

Data Index: 922328 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 5.7145. Min Range: -5.7145

Max Act: 5.2458. Min Act: -0.1700

Data Index: 845830 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 5.7145. Min Range: -5.7145

Max Act: 5.2145. Min Act: -0.1700

Data Index: 381193 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 5.7145. Min Range: -5.7145

Max Act: 5.1208. Min Act: -0.1700

Data Index: 707042 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 5.7145. Min Range: -5.7145

Max Act: 5.0895. Min Act: -0.1700

Data Index: 590354 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 5.7145. Min Range: -5.7145

Max Act: 5.0270. Min Act: -0.1700

Data Index: 531900 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 5.7145. Min Range: -5.7145

Max Act: 4.9645. Min Act: -0.1700

Data Index: 198187 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 5.7145. Min Range: -5.7145

Max Act: 4.9333. Min Act: -0.1700

Data Index: 706322 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 5.7145. Min Range: -5.7145

Max Act: 4.8708. Min Act: -0.1700

Data Index: 967181 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 5.7145. Min Range: -5.7145

Max Act: 4.9645. Min Act: -0.1700

Data Index: 1018712 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 5.7145. Min Range: -5.7145

Max Act: 4.9645. Min Act: -0.1700

Data Index: 103916 (C4 (Web Text))

Max Activating Token Index: 153