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

Dataset: Open Web Text

Neuron 1978 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: 3.6626. Min Range: -3.6626

Max Act: 3.6626. Min Act: -0.1700

Data Index: 1241603 (Open Web Text)

Max Activating Token Index: 205

Text #1

Max Range: 3.6626. Min Range: -3.6626

Max Act: 3.6291. Min Act: -0.1700

Data Index: 6791336 (Open Web Text)

Max Activating Token Index: 113

Text #2

Max Range: 3.6626. Min Range: -3.6626

Max Act: 3.6323. Min Act: -0.1700

Data Index: 8618926 (Open Web Text)

Max Activating Token Index: 908

Text #3

Max Range: 3.6626. Min Range: -3.6626

Max Act: 3.6237. Min Act: -0.1700

Data Index: 10295 (Open Web Text)

Max Activating Token Index: 656

Text #4

Max Range: 3.6626. Min Range: -3.6626

Max Act: 3.5602. Min Act: -0.1700

Data Index: 8784310 (Open Web Text)

Max Activating Token Index: 406

Text #5

Max Range: 3.6626. Min Range: -3.6626

Max Act: 3.5623. Min Act: -0.1700

Data Index: 395408 (Open Web Text)

Max Activating Token Index: 992

Text #6

Max Range: 3.6626. Min Range: -3.6626

Max Act: 3.5746. Min Act: -0.1700

Data Index: 1424378 (Open Web Text)

Max Activating Token Index: 80

Text #7

Max Range: 3.6626. Min Range: -3.6626

Max Act: 3.5629. Min Act: -0.1700

Data Index: 2696691 (Open Web Text)

Max Activating Token Index: 956

Text #8

Max Range: 3.6626. Min Range: -3.6626

Max Act: 3.5455. Min Act: -0.1700

Data Index: 5210425 (Open Web Text)

Max Activating Token Index: 429

Text #9

Max Range: 3.6626. Min Range: -3.6626

Max Act: 3.5545. Min Act: -0.1700

Data Index: 5278647 (Open Web Text)

Max Activating Token Index: 588

Text #10

Max Range: 3.6626. Min Range: -3.6626

Max Act: 3.5642. Min Act: -0.1700

Data Index: 7183131 (Open Web Text)

Max Activating Token Index: 658

Text #11

Max Range: 3.6626. Min Range: -3.6626

Max Act: 3.5597. Min Act: -0.1700

Data Index: 877384 (Open Web Text)

Max Activating Token Index: 539

Text #12

Max Range: 3.6626. Min Range: -3.6626

Max Act: 3.5360. Min Act: -0.1700

Data Index: 4795960 (Open Web Text)

Max Activating Token Index: 123

Text #13

Max Range: 3.6626. Min Range: -3.6626

Max Act: 3.5359. Min Act: -0.1700

Data Index: 6058547 (Open Web Text)

Max Activating Token Index: 102

Text #14

Max Range: 3.6626. Min Range: -3.6626

Max Act: 3.5351. Min Act: -0.1700

Data Index: 7893394 (Open Web Text)

Max Activating Token Index: 611

Text #15

Max Range: 3.6626. Min Range: -3.6626

Max Act: 3.5413. Min Act: -0.1700

Data Index: 4295861 (Open Web Text)

Max Activating Token Index: 981

Text #16

Max Range: 3.6626. Min Range: -3.6626

Max Act: 3.5059. Min Act: -0.1700

Data Index: 3484661 (Open Web Text)

Max Activating Token Index: 561

Text #17

Max Range: 3.6626. Min Range: -3.6626

Max Act: 3.5194. Min Act: -0.1700

Data Index: 6357330 (Open Web Text)

Max Activating Token Index: 597

Text #18

Max Range: 3.6626. Min Range: -3.6626

Max Act: 3.5111. Min Act: -0.1700

Data Index: 5676134 (Open Web Text)

Max Activating Token Index: 633

Text #19

Max Range: 3.6626. Min Range: -3.6626

Max Act: 3.5051. Min Act: -0.1700

Data Index: 8768687 (Open Web Text)

Max Activating Token Index: 449