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

Dataset: Open Web Text

Neuron 2651 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: 3.9463. Min Range: -3.9463

Max Act: 3.9463. Min Act: -0.1700

Data Index: 4453998 (Open Web Text)

Max Activating Token Index: 811

Text #1

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.8524. Min Act: -0.1700

Data Index: 6606184 (Open Web Text)

Max Activating Token Index: 799

Text #2

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.8037. Min Act: -0.1700

Data Index: 1491177 (Open Web Text)

Max Activating Token Index: 157

Text #3

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.8063. Min Act: -0.1700

Data Index: 4404286 (Open Web Text)

Max Activating Token Index: 691

Text #4

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.8007. Min Act: -0.1700

Data Index: 2666468 (Open Web Text)

Max Activating Token Index: 795

Text #5

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.7971. Min Act: -0.1700

Data Index: 319051 (Open Web Text)

Max Activating Token Index: 636

Text #6

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.7678. Min Act: -0.1700

Data Index: 1123034 (Open Web Text)

Max Activating Token Index: 41

Text #7

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.7710. Min Act: -0.1700

Data Index: 5497756 (Open Web Text)

Max Activating Token Index: 108

Text #8

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.7854. Min Act: -0.1700

Data Index: 2260599 (Open Web Text)

Max Activating Token Index: 145

Text #9

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.7675. Min Act: -0.1700

Data Index: 8308065 (Open Web Text)

Max Activating Token Index: 886

Text #10

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.7875. Min Act: -0.1700

Data Index: 925054 (Open Web Text)

Max Activating Token Index: 865

Text #11

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.7719. Min Act: -0.1700

Data Index: 7570752 (Open Web Text)

Max Activating Token Index: 450

Text #12

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.7823. Min Act: -0.1700

Data Index: 3963777 (Open Web Text)

Max Activating Token Index: 564

Text #13

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.7533. Min Act: -0.1700

Data Index: 7286474 (Open Web Text)

Max Activating Token Index: 738

Text #14

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.7426. Min Act: -0.1700

Data Index: 7975585 (Open Web Text)

Max Activating Token Index: 58

Text #15

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.7294. Min Act: -0.1700

Data Index: 7971948 (Open Web Text)

Max Activating Token Index: 304

Text #16

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.7609. Min Act: -0.1700

Data Index: 4715246 (Open Web Text)

Max Activating Token Index: 33

Text #17

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.7475. Min Act: -0.1700

Data Index: 7676227 (Open Web Text)

Max Activating Token Index: 329

Text #18

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.7519. Min Act: -0.1700

Data Index: 1028099 (Open Web Text)

Max Activating Token Index: 131

Text #19

Max Range: 3.9463. Min Range: -3.9463

Max Act: 3.7435. Min Act: -0.1700

Data Index: 4988287 (Open Web Text)

Max Activating Token Index: 655