Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 5567 in Layer 41

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')

Text #0

Max Range: 7.2181. Min Range: -7.2181

Max Act: 7.2181. Min Act: -0.1700

Data Index: 6924214 (Open Web Text)

Max Activating Token Index: 804

Text #1

Max Range: 7.2181. Min Range: -7.2181

Max Act: 7.0619. Min Act: -0.1700

Data Index: 1727412 (Open Web Text)

Max Activating Token Index: 106

Text #2

Max Range: 7.2181. Min Range: -7.2181

Max Act: 6.9369. Min Act: -0.1700

Data Index: 8342702 (Open Web Text)

Max Activating Token Index: 419

Text #3

Max Range: 7.2181. Min Range: -7.2181

Max Act: 6.8744. Min Act: -0.1700

Data Index: 2110440 (Open Web Text)

Max Activating Token Index: 881

Text #4

Max Range: 7.2181. Min Range: -7.2181

Max Act: 6.8431. Min Act: -0.1700

Data Index: 8057024 (Open Web Text)

Max Activating Token Index: 558

Text #5

Max Range: 7.2181. Min Range: -7.2181

Max Act: 6.7181. Min Act: -0.1700

Data Index: 4559721 (Open Web Text)

Max Activating Token Index: 1016

Text #6

Max Range: 7.2181. Min Range: -7.2181

Max Act: 6.7181. Min Act: -0.1700

Data Index: 8681849 (Open Web Text)

Max Activating Token Index: 159

Text #7

Max Range: 7.2181. Min Range: -7.2181

Max Act: 6.6869. Min Act: -0.1700

Data Index: 1086802 (Open Web Text)

Max Activating Token Index: 101

Text #8

Max Range: 7.2181. Min Range: -7.2181

Max Act: 6.7181. Min Act: -0.1700

Data Index: 5613128 (Open Web Text)

Max Activating Token Index: 745

Text #9

Max Range: 7.2181. Min Range: -7.2181

Max Act: 6.6869. Min Act: -0.1700

Data Index: 4961582 (Open Web Text)

Max Activating Token Index: 418

Text #10

Max Range: 7.2181. Min Range: -7.2181

Max Act: 6.5931. Min Act: -0.1700

Data Index: 2328473 (Open Web Text)

Max Activating Token Index: 611

Text #11

Max Range: 7.2181. Min Range: -7.2181

Max Act: 6.5931. Min Act: -0.1700

Data Index: 7425195 (Open Web Text)

Max Activating Token Index: 120

Text #12

Max Range: 7.2181. Min Range: -7.2181

Max Act: 6.5619. Min Act: -0.1700

Data Index: 4819189 (Open Web Text)

Max Activating Token Index: 123

Text #13

Max Range: 7.2181. Min Range: -7.2181

Max Act: 6.5619. Min Act: -0.1700

Data Index: 2078082 (Open Web Text)

Max Activating Token Index: 379

Text #14

Max Range: 7.2181. Min Range: -7.2181

Max Act: 6.5306. Min Act: -0.1700

Data Index: 4102427 (Open Web Text)

Max Activating Token Index: 170

Text #15

Max Range: 7.2181. Min Range: -7.2181

Max Act: 6.4994. Min Act: -0.1700

Data Index: 7396816 (Open Web Text)

Max Activating Token Index: 747

Text #16

Max Range: 7.2181. Min Range: -7.2181

Max Act: 6.4994. Min Act: -0.1700

Data Index: 8523148 (Open Web Text)

Max Activating Token Index: 671

Text #17

Max Range: 7.2181. Min Range: -7.2181

Max Act: 6.4681. Min Act: -0.1700

Data Index: 8757526 (Open Web Text)

Max Activating Token Index: 190

Text #18

Max Range: 7.2181. Min Range: -7.2181

Max Act: 6.4369. Min Act: -0.1699

Data Index: 4833723 (Open Web Text)

Max Activating Token Index: 860

Text #19

Max Range: 7.2181. Min Range: -7.2181

Max Act: 6.4369. Min Act: -0.1700

Data Index: 8047860 (Open Web Text)

Max Activating Token Index: 557