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

Dataset: Open Web Text

Neuron 1835 in Layer 1

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: 4.8858. Min Range: -4.8858

Max Act: 4.8597. Min Act: -0.1700

Data Index: 5244462 (Open Web Text)

Max Activating Token Index: 906

Text #1

Max Range: 4.8858. Min Range: -4.8858

Max Act: 4.8858. Min Act: -0.1700

Data Index: 8491717 (Open Web Text)

Max Activating Token Index: 863

Text #2

Max Range: 4.8858. Min Range: -4.8858

Max Act: 4.7981. Min Act: -0.1700

Data Index: 4184569 (Open Web Text)

Max Activating Token Index: 461

Text #3

Max Range: 4.8858. Min Range: -4.8858

Max Act: 4.8169. Min Act: -0.1700

Data Index: 3376702 (Open Web Text)

Max Activating Token Index: 442

Text #4

Max Range: 4.8858. Min Range: -4.8858

Max Act: 4.7720. Min Act: -0.1700

Data Index: 8772038 (Open Web Text)

Max Activating Token Index: 502

Text #5

Max Range: 4.8858. Min Range: -4.8858

Max Act: 4.7742. Min Act: -0.1700

Data Index: 5056912 (Open Web Text)

Max Activating Token Index: 527

Text #6

Max Range: 4.8858. Min Range: -4.8858

Max Act: 4.7551. Min Act: -0.1700

Data Index: 4366200 (Open Web Text)

Max Activating Token Index: 716

Text #7

Max Range: 4.8858. Min Range: -4.8858

Max Act: 4.7304. Min Act: -0.1700

Data Index: 6022005 (Open Web Text)

Max Activating Token Index: 919

Text #8

Max Range: 4.8858. Min Range: -4.8858

Max Act: 4.7437. Min Act: -0.1700

Data Index: 619558 (Open Web Text)

Max Activating Token Index: 859

Text #9

Max Range: 4.8858. Min Range: -4.8858

Max Act: 4.7463. Min Act: -0.1700

Data Index: 4058395 (Open Web Text)

Max Activating Token Index: 582

Text #10

Max Range: 4.8858. Min Range: -4.8858

Max Act: 4.7464. Min Act: -0.1700

Data Index: 8072182 (Open Web Text)

Max Activating Token Index: 346

Text #11

Max Range: 4.8858. Min Range: -4.8858

Max Act: 4.7363. Min Act: -0.1700

Data Index: 6725293 (Open Web Text)

Max Activating Token Index: 375

Text #12

Max Range: 4.8858. Min Range: -4.8858

Max Act: 4.7681. Min Act: -0.1700

Data Index: 3330202 (Open Web Text)

Max Activating Token Index: 389

Text #13

Max Range: 4.8858. Min Range: -4.8858

Max Act: 4.7333. Min Act: -0.1700

Data Index: 6651481 (Open Web Text)

Max Activating Token Index: 902

Text #14

Max Range: 4.8858. Min Range: -4.8858

Max Act: 4.7306. Min Act: -0.1700

Data Index: 6475785 (Open Web Text)

Max Activating Token Index: 550

Text #15

Max Range: 4.8858. Min Range: -4.8858

Max Act: 4.7433. Min Act: -0.1700

Data Index: 2370407 (Open Web Text)

Max Activating Token Index: 538

Text #16

Max Range: 4.8858. Min Range: -4.8858

Max Act: 4.6841. Min Act: -0.1700

Data Index: 1972833 (Open Web Text)

Max Activating Token Index: 404

Text #17

Max Range: 4.8858. Min Range: -4.8858

Max Act: 4.7232. Min Act: -0.1700

Data Index: 2135611 (Open Web Text)

Max Activating Token Index: 472

Text #18

Max Range: 4.8858. Min Range: -4.8858

Max Act: 4.7056. Min Act: -0.1700

Data Index: 2139397 (Open Web Text)

Max Activating Token Index: 173

Text #19

Max Range: 4.8858. Min Range: -4.8858

Max Act: 4.7043. Min Act: -0.1700

Data Index: 1268404 (Open Web Text)

Max Activating Token Index: 356