Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 867 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.7281. Min Range: -3.7281

Max Act: 3.7281. Min Act: -0.1700

Data Index: 2172883 (Open Web Text)

Max Activating Token Index: 721

Text #1

Max Range: 3.7281. Min Range: -3.7281

Max Act: 3.6175. Min Act: -0.1700

Data Index: 6956568 (Open Web Text)

Max Activating Token Index: 914

Text #2

Max Range: 3.7281. Min Range: -3.7281

Max Act: 3.5862. Min Act: -0.1700

Data Index: 7260219 (Open Web Text)

Max Activating Token Index: 83

Text #3

Max Range: 3.7281. Min Range: -3.7281

Max Act: 3.6036. Min Act: -0.1700

Data Index: 4075389 (Open Web Text)

Max Activating Token Index: 462

Text #4

Max Range: 3.7281. Min Range: -3.7281

Max Act: 3.5479. Min Act: -0.1700

Data Index: 2283184 (Open Web Text)

Max Activating Token Index: 963

Text #5

Max Range: 3.7281. Min Range: -3.7281

Max Act: 3.5483. Min Act: -0.1700

Data Index: 8464236 (Open Web Text)

Max Activating Token Index: 991

Text #6

Max Range: 3.7281. Min Range: -3.7281

Max Act: 3.5774. Min Act: -0.1700

Data Index: 8154888 (Open Web Text)

Max Activating Token Index: 627

Text #7

Max Range: 3.7281. Min Range: -3.7281

Max Act: 3.5663. Min Act: -0.1700

Data Index: 8369512 (Open Web Text)

Max Activating Token Index: 183

Text #8

Max Range: 3.7281. Min Range: -3.7281

Max Act: 3.5608. Min Act: -0.1700

Data Index: 3704544 (Open Web Text)

Max Activating Token Index: 580

Text #9

Max Range: 3.7281. Min Range: -3.7281

Max Act: 3.5496. Min Act: -0.1700

Data Index: 977439 (Open Web Text)

Max Activating Token Index: 71

Text #10

Max Range: 3.7281. Min Range: -3.7281

Max Act: 3.5594. Min Act: -0.1700

Data Index: 8412250 (Open Web Text)

Max Activating Token Index: 401

Text #11

Max Range: 3.7281. Min Range: -3.7281

Max Act: 3.5280. Min Act: -0.1700

Data Index: 4813610 (Open Web Text)

Max Activating Token Index: 485

Text #12

Max Range: 3.7281. Min Range: -3.7281

Max Act: 3.5593. Min Act: -0.1700

Data Index: 1621554 (Open Web Text)

Max Activating Token Index: 917

Text #13

Max Range: 3.7281. Min Range: -3.7281

Max Act: 3.5330. Min Act: -0.1700

Data Index: 5481340 (Open Web Text)

Max Activating Token Index: 55

Text #14

Max Range: 3.7281. Min Range: -3.7281

Max Act: 3.5162. Min Act: -0.1700

Data Index: 2753737 (Open Web Text)

Max Activating Token Index: 484

Text #15

Max Range: 3.7281. Min Range: -3.7281

Max Act: 3.5203. Min Act: -0.1700

Data Index: 3806732 (Open Web Text)

Max Activating Token Index: 111

Text #16

Max Range: 3.7281. Min Range: -3.7281

Max Act: 3.5382. Min Act: -0.1700

Data Index: 3532114 (Open Web Text)

Max Activating Token Index: 697

Text #17

Max Range: 3.7281. Min Range: -3.7281

Max Act: 3.5182. Min Act: -0.1700

Data Index: 5224408 (Open Web Text)

Max Activating Token Index: 66

Text #18

Max Range: 3.7281. Min Range: -3.7281

Max Act: 3.5222. Min Act: -0.1700

Data Index: 2307512 (Open Web Text)

Max Activating Token Index: 609

Text #19

Max Range: 3.7281. Min Range: -3.7281

Max Act: 3.5100. Min Act: -0.1700

Data Index: 5207846 (Open Web Text)

Max Activating Token Index: 820