Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer

Dataset: Open Web Text

Neuron 3647 in Layer 22

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')

Text #0

Max Range: 7.3390. Min Range: -7.3390

Max Act: 7.3390. Min Act: -0.1700

Data Index: 87743 (Open Web Text)

Max Activating Token Index: 122

Text #1

Max Range: 7.3390. Min Range: -7.3390

Max Act: 7.0265. Min Act: -0.1700

Data Index: 6850060 (Open Web Text)

Max Activating Token Index: 367

Text #2

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.8078. Min Act: -0.1700

Data Index: 6850054 (Open Web Text)

Max Activating Token Index: 336

Text #3

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.7453. Min Act: -0.1700

Data Index: 5300660 (Open Web Text)

Max Activating Token Index: 678

Text #4

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.6203. Min Act: -0.1700

Data Index: 5220454 (Open Web Text)

Max Activating Token Index: 520

Text #5

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.5890. Min Act: -0.1700

Data Index: 8439545 (Open Web Text)

Max Activating Token Index: 251

Text #6

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.6203. Min Act: -0.1700

Data Index: 1987829 (Open Web Text)

Max Activating Token Index: 122

Text #7

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.4953. Min Act: -0.1700

Data Index: 6850052 (Open Web Text)

Max Activating Token Index: 351

Text #8

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.4640. Min Act: -0.1700

Data Index: 6850083 (Open Web Text)

Max Activating Token Index: 301

Text #9

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.4015. Min Act: -0.1700

Data Index: 6850078 (Open Web Text)

Max Activating Token Index: 70

Text #10

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.4640. Min Act: -0.1700

Data Index: 1961046 (Open Web Text)

Max Activating Token Index: 1022

Text #11

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.3390. Min Act: -0.1700

Data Index: 6850066 (Open Web Text)

Max Activating Token Index: 103

Text #12

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.3703. Min Act: -0.1700

Data Index: 6850077 (Open Web Text)

Max Activating Token Index: 634

Text #13

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.3703. Min Act: -0.1700

Data Index: 6850076 (Open Web Text)

Max Activating Token Index: 975

Text #14

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.3390. Min Act: -0.1700

Data Index: 6850079 (Open Web Text)

Max Activating Token Index: 276

Text #15

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.3078. Min Act: -0.1700

Data Index: 4639352 (Open Web Text)

Max Activating Token Index: 837

Text #16

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.2765. Min Act: -0.1700

Data Index: 3127986 (Open Web Text)

Max Activating Token Index: 582

Text #17

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.2453. Min Act: -0.1700

Data Index: 6850062 (Open Web Text)

Max Activating Token Index: 540

Text #18

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.2453. Min Act: -0.1700

Data Index: 5703382 (Open Web Text)

Max Activating Token Index: 28

Text #19

Max Range: 7.3390. Min Range: -7.3390

Max Act: 6.2453. Min Act: -0.1700

Data Index: 6850056 (Open Web Text)

Max Activating Token Index: 662