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

Dataset: Open Web Text

Neuron 1198 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: 1.1624. Min Range: -1.1624

Max Act: 1.1624. Min Act: -0.1700

Data Index: 5886370 (Open Web Text)

Max Activating Token Index: 898

Text #1

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.1164. Min Act: -0.1700

Data Index: 5471463 (Open Web Text)

Max Activating Token Index: 990

Text #2

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0900. Min Act: -0.1700

Data Index: 8244576 (Open Web Text)

Max Activating Token Index: 57

Text #3

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0586. Min Act: -0.1700

Data Index: 8260798 (Open Web Text)

Max Activating Token Index: 607

Text #4

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0699. Min Act: -0.1700

Data Index: 1693621 (Open Web Text)

Max Activating Token Index: 825

Text #5

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0680. Min Act: -0.1700

Data Index: 3271867 (Open Web Text)

Max Activating Token Index: 600

Text #6

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0281. Min Act: -0.1700

Data Index: 348609 (Open Web Text)

Max Activating Token Index: 552

Text #7

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0613. Min Act: -0.1699

Data Index: 8521618 (Open Web Text)

Max Activating Token Index: 766

Text #8

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0529. Min Act: -0.1700

Data Index: 3942530 (Open Web Text)

Max Activating Token Index: 571

Text #9

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0681. Min Act: -0.1700

Data Index: 7678372 (Open Web Text)

Max Activating Token Index: 293

Text #10

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0442. Min Act: -0.1700

Data Index: 7398867 (Open Web Text)

Max Activating Token Index: 553

Text #11

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0405. Min Act: -0.1700

Data Index: 7685509 (Open Web Text)

Max Activating Token Index: 327

Text #12

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0505. Min Act: -0.1700

Data Index: 157539 (Open Web Text)

Max Activating Token Index: 407

Text #13

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0322. Min Act: -0.1700

Data Index: 1101848 (Open Web Text)

Max Activating Token Index: 555

Text #14

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0427. Min Act: -0.1699

Data Index: 6848913 (Open Web Text)

Max Activating Token Index: 677

Text #15

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0285. Min Act: -0.1700

Data Index: 1735121 (Open Web Text)

Max Activating Token Index: 657

Text #16

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0313. Min Act: -0.1700

Data Index: 870117 (Open Web Text)

Max Activating Token Index: 492

Text #17

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0232. Min Act: -0.1700

Data Index: 7685510 (Open Web Text)

Max Activating Token Index: 371

Text #18

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0092. Min Act: -0.1700

Data Index: 6598716 (Open Web Text)

Max Activating Token Index: 667

Text #19

Max Range: 1.1624. Min Range: -1.1624

Max Act: 1.0111. Min Act: -0.1699

Data Index: 4452512 (Open Web Text)

Max Activating Token Index: 462