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

Dataset: Open Web Text

Neuron 1867 in Layer 2

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: 4.2707. Min Range: -4.2707

Max Act: 4.2557. Min Act: -0.1700

Data Index: 531010 (Open Web Text)

Max Activating Token Index: 1013

Text #1

Max Range: 4.2707. Min Range: -4.2707

Max Act: 4.2707. Min Act: -0.1700

Data Index: 2394074 (Open Web Text)

Max Activating Token Index: 527

Text #2

Max Range: 4.2707. Min Range: -4.2707

Max Act: 4.0521. Min Act: -0.1700

Data Index: 5892338 (Open Web Text)

Max Activating Token Index: 422

Text #3

Max Range: 4.2707. Min Range: -4.2707

Max Act: 4.0322. Min Act: -0.1700

Data Index: 6709479 (Open Web Text)

Max Activating Token Index: 1010

Text #4

Max Range: 4.2707. Min Range: -4.2707

Max Act: 4.0421. Min Act: -0.1700

Data Index: 4482077 (Open Web Text)

Max Activating Token Index: 467

Text #5

Max Range: 4.2707. Min Range: -4.2707

Max Act: 4.0522. Min Act: -0.1700

Data Index: 688041 (Open Web Text)

Max Activating Token Index: 529

Text #6

Max Range: 4.2707. Min Range: -4.2707

Max Act: 4.0029. Min Act: -0.1700

Data Index: 2947878 (Open Web Text)

Max Activating Token Index: 596

Text #7

Max Range: 4.2707. Min Range: -4.2707

Max Act: 4.0069. Min Act: -0.1700

Data Index: 2323020 (Open Web Text)

Max Activating Token Index: 653

Text #8

Max Range: 4.2707. Min Range: -4.2707

Max Act: 4.0203. Min Act: -0.1700

Data Index: 7453718 (Open Web Text)

Max Activating Token Index: 87

Text #9

Max Range: 4.2707. Min Range: -4.2707

Max Act: 4.0096. Min Act: -0.1700

Data Index: 8009241 (Open Web Text)

Max Activating Token Index: 725

Text #10

Max Range: 4.2707. Min Range: -4.2707

Max Act: 3.9854. Min Act: -0.1700

Data Index: 54044 (Open Web Text)

Max Activating Token Index: 602

Text #11

Max Range: 4.2707. Min Range: -4.2707

Max Act: 3.9928. Min Act: -0.1700

Data Index: 2047962 (Open Web Text)

Max Activating Token Index: 587

Text #12

Max Range: 4.2707. Min Range: -4.2707

Max Act: 3.9728. Min Act: -0.1700

Data Index: 1097279 (Open Web Text)

Max Activating Token Index: 154

Text #13

Max Range: 4.2707. Min Range: -4.2707

Max Act: 3.9867. Min Act: -0.1700

Data Index: 1048681 (Open Web Text)

Max Activating Token Index: 953

Text #14

Max Range: 4.2707. Min Range: -4.2707

Max Act: 3.9886. Min Act: -0.1700

Data Index: 8703038 (Open Web Text)

Max Activating Token Index: 507

Text #15

Max Range: 4.2707. Min Range: -4.2707

Max Act: 3.9727. Min Act: -0.1700

Data Index: 2015080 (Open Web Text)

Max Activating Token Index: 887

Text #16

Max Range: 4.2707. Min Range: -4.2707

Max Act: 3.9734. Min Act: -0.1700

Data Index: 6741618 (Open Web Text)

Max Activating Token Index: 577

Text #17

Max Range: 4.2707. Min Range: -4.2707

Max Act: 3.9451. Min Act: -0.1700

Data Index: 6491438 (Open Web Text)

Max Activating Token Index: 930

Text #18

Max Range: 4.2707. Min Range: -4.2707

Max Act: 3.9600. Min Act: -0.1700

Data Index: 3899666 (Open Web Text)

Max Activating Token Index: 400

Text #19

Max Range: 4.2707. Min Range: -4.2707

Max Act: 3.9934. Min Act: -0.1700

Data Index: 5311976 (Open Web Text)

Max Activating Token Index: 751