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

Dataset: Open Web Text

Neuron 6 in Layer 0

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: 4.4695. Min Range: -4.4695

Max Act: 4.4695. Min Act: -0.1700

Data Index: 8725318 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 4.4695. Min Range: -4.4695

Max Act: 4.4140. Min Act: -0.1700

Data Index: 6407922 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.4695. Min Range: -4.4695

Max Act: 4.4247. Min Act: -0.1700

Data Index: 2745940 (Open Web Text)

Max Activating Token Index: 1020

Text #3

Max Range: 4.4695. Min Range: -4.4695

Max Act: 4.4304. Min Act: -0.1700

Data Index: 1388729 (Open Web Text)

Max Activating Token Index: 563

Text #4

Max Range: 4.4695. Min Range: -4.4695

Max Act: 4.4156. Min Act: -0.1700

Data Index: 777934 (Open Web Text)

Max Activating Token Index: 12

Text #5

Max Range: 4.4695. Min Range: -4.4695

Max Act: 4.3758. Min Act: -0.1700

Data Index: 4177514 (Open Web Text)

Max Activating Token Index: 949

Text #6

Max Range: 4.4695. Min Range: -4.4695

Max Act: 4.3966. Min Act: -0.1700

Data Index: 5053220 (Open Web Text)

Max Activating Token Index: 10

Text #7

Max Range: 4.4695. Min Range: -4.4695

Max Act: 4.3899. Min Act: -0.1700

Data Index: 1015025 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.4695. Min Range: -4.4695

Max Act: 4.3813. Min Act: -0.1700

Data Index: 5527848 (Open Web Text)

Max Activating Token Index: 615

Text #9

Max Range: 4.4695. Min Range: -4.4695

Max Act: 4.4064. Min Act: -0.1700

Data Index: 1659082 (Open Web Text)

Max Activating Token Index: 714

Text #10

Max Range: 4.4695. Min Range: -4.4695

Max Act: 4.3510. Min Act: -0.1700

Data Index: 1973670 (Open Web Text)

Max Activating Token Index: 685

Text #11

Max Range: 4.4695. Min Range: -4.4695

Max Act: 4.3736. Min Act: -0.1700

Data Index: 1980774 (Open Web Text)

Max Activating Token Index: 668

Text #12

Max Range: 4.4695. Min Range: -4.4695

Max Act: 4.3750. Min Act: -0.1700

Data Index: 6332331 (Open Web Text)

Max Activating Token Index: 680

Text #13

Max Range: 4.4695. Min Range: -4.4695

Max Act: 4.3728. Min Act: -0.1700

Data Index: 5111631 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 4.4695. Min Range: -4.4695

Max Act: 4.3295. Min Act: -0.1700

Data Index: 1117965 (Open Web Text)

Max Activating Token Index: 12

Text #15

Max Range: 4.4695. Min Range: -4.4695

Max Act: 4.3341. Min Act: -0.1700

Data Index: 2389961 (Open Web Text)

Max Activating Token Index: 1014

Text #16

Max Range: 4.4695. Min Range: -4.4695

Max Act: 4.3316. Min Act: -0.1700

Data Index: 183136 (Open Web Text)

Max Activating Token Index: 830

Text #17

Max Range: 4.4695. Min Range: -4.4695

Max Act: 4.3239. Min Act: -0.1700

Data Index: 3729074 (Open Web Text)

Max Activating Token Index: 679

Text #18

Max Range: 4.4695. Min Range: -4.4695

Max Act: 4.3333. Min Act: -0.1700

Data Index: 4332712 (Open Web Text)

Max Activating Token Index: 996

Text #19

Max Range: 4.4695. Min Range: -4.4695

Max Act: 4.3352. Min Act: -0.1700

Data Index: 6240732 (Open Web Text)

Max Activating Token Index: 29