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

Dataset: Open Web Text

Neuron 1123 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: 4.8978. Min Range: -4.8978

Max Act: 4.8978. Min Act: -0.1700

Data Index: 3750078 (Open Web Text)

Max Activating Token Index: 662

Text #1

Max Range: 4.8978. Min Range: -4.8978

Max Act: 4.8316. Min Act: -0.1700

Data Index: 7533516 (Open Web Text)

Max Activating Token Index: 543

Text #2

Max Range: 4.8978. Min Range: -4.8978

Max Act: 4.6523. Min Act: -0.1700

Data Index: 1841476 (Open Web Text)

Max Activating Token Index: 788

Text #3

Max Range: 4.8978. Min Range: -4.8978

Max Act: 4.6605. Min Act: -0.1700

Data Index: 7808044 (Open Web Text)

Max Activating Token Index: 376

Text #4

Max Range: 4.8978. Min Range: -4.8978

Max Act: 4.6010. Min Act: -0.1700

Data Index: 7203758 (Open Web Text)

Max Activating Token Index: 505

Text #5

Max Range: 4.8978. Min Range: -4.8978

Max Act: 4.5618. Min Act: -0.1700

Data Index: 8358087 (Open Web Text)

Max Activating Token Index: 993

Text #6

Max Range: 4.8978. Min Range: -4.8978

Max Act: 4.6108. Min Act: -0.1700

Data Index: 2113801 (Open Web Text)

Max Activating Token Index: 331

Text #7

Max Range: 4.8978. Min Range: -4.8978

Max Act: 4.6111. Min Act: -0.1700

Data Index: 3305868 (Open Web Text)

Max Activating Token Index: 781

Text #8

Max Range: 4.8978. Min Range: -4.8978

Max Act: 4.5914. Min Act: -0.1700

Data Index: 7580084 (Open Web Text)

Max Activating Token Index: 1003

Text #9

Max Range: 4.8978. Min Range: -4.8978

Max Act: 4.5265. Min Act: -0.1700

Data Index: 2463330 (Open Web Text)

Max Activating Token Index: 372

Text #10

Max Range: 4.8978. Min Range: -4.8978

Max Act: 4.4654. Min Act: -0.1700

Data Index: 4388341 (Open Web Text)

Max Activating Token Index: 998

Text #11

Max Range: 4.8978. Min Range: -4.8978

Max Act: 4.5029. Min Act: -0.1700

Data Index: 7418178 (Open Web Text)

Max Activating Token Index: 830

Text #12

Max Range: 4.8978. Min Range: -4.8978

Max Act: 4.4843. Min Act: -0.1700

Data Index: 4615577 (Open Web Text)

Max Activating Token Index: 355

Text #13

Max Range: 4.8978. Min Range: -4.8978

Max Act: 4.4426. Min Act: -0.1700

Data Index: 3513372 (Open Web Text)

Max Activating Token Index: 76

Text #14

Max Range: 4.8978. Min Range: -4.8978

Max Act: 4.4950. Min Act: -0.1700

Data Index: 1903430 (Open Web Text)

Max Activating Token Index: 976

Text #15

Max Range: 4.8978. Min Range: -4.8978

Max Act: 4.4478. Min Act: -0.1700

Data Index: 3677046 (Open Web Text)

Max Activating Token Index: 781

Text #16

Max Range: 4.8978. Min Range: -4.8978

Max Act: 4.4477. Min Act: -0.1700

Data Index: 5089074 (Open Web Text)

Max Activating Token Index: 577

Text #17

Max Range: 4.8978. Min Range: -4.8978

Max Act: 4.4322. Min Act: -0.1698

Data Index: 8324400 (Open Web Text)

Max Activating Token Index: 479

Text #18

Max Range: 4.8978. Min Range: -4.8978

Max Act: 4.4433. Min Act: -0.1700

Data Index: 501638 (Open Web Text)

Max Activating Token Index: 104

Text #19

Max Range: 4.8978. Min Range: -4.8978

Max Act: 4.4234. Min Act: -0.1700

Data Index: 1653882 (Open Web Text)

Max Activating Token Index: 225