Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer

Dataset: Open Web Text

Neuron 3796 in Layer 26

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3442. Min Range: -7.3442

Max Act: 7.3442. Min Act: -0.1700

Data Index: 1883969 (Open Web Text)

Max Activating Token Index: 533

Text #1

Max Range: 7.3442. Min Range: -7.3442

Max Act: 7.2817. Min Act: -0.1700

Data Index: 334983 (Open Web Text)

Max Activating Token Index: 587

Text #2

Max Range: 7.3442. Min Range: -7.3442

Max Act: 7.2817. Min Act: -0.1700

Data Index: 1702110 (Open Web Text)

Max Activating Token Index: 590

Text #3

Max Range: 7.3442. Min Range: -7.3442

Max Act: 7.2504. Min Act: -0.1700

Data Index: 1026969 (Open Web Text)

Max Activating Token Index: 979

Text #4

Max Range: 7.3442. Min Range: -7.3442

Max Act: 7.1879. Min Act: -0.1700

Data Index: 5176307 (Open Web Text)

Max Activating Token Index: 189

Text #5

Max Range: 7.3442. Min Range: -7.3442

Max Act: 7.2192. Min Act: -0.1700

Data Index: 4727485 (Open Web Text)

Max Activating Token Index: 786

Text #6

Max Range: 7.3442. Min Range: -7.3442

Max Act: 7.2192. Min Act: -0.1700

Data Index: 6696391 (Open Web Text)

Max Activating Token Index: 640

Text #7

Max Range: 7.3442. Min Range: -7.3442

Max Act: 7.1567. Min Act: -0.1700

Data Index: 1674428 (Open Web Text)

Max Activating Token Index: 154

Text #8

Max Range: 7.3442. Min Range: -7.3442

Max Act: 7.1567. Min Act: -0.1700

Data Index: 4651343 (Open Web Text)

Max Activating Token Index: 461

Text #9

Max Range: 7.3442. Min Range: -7.3442

Max Act: 7.1567. Min Act: -0.1700

Data Index: 7928310 (Open Web Text)

Max Activating Token Index: 111

Text #10

Max Range: 7.3442. Min Range: -7.3442

Max Act: 7.1254. Min Act: -0.1700

Data Index: 7065217 (Open Web Text)

Max Activating Token Index: 868

Text #11

Max Range: 7.3442. Min Range: -7.3442

Max Act: 7.1254. Min Act: -0.1700

Data Index: 1968571 (Open Web Text)

Max Activating Token Index: 663

Text #12

Max Range: 7.3442. Min Range: -7.3442

Max Act: 7.0942. Min Act: -0.1700

Data Index: 5115452 (Open Web Text)

Max Activating Token Index: 721

Text #13

Max Range: 7.3442. Min Range: -7.3442

Max Act: 7.0942. Min Act: -0.1700

Data Index: 702902 (Open Web Text)

Max Activating Token Index: 1006

Text #14

Max Range: 7.3442. Min Range: -7.3442

Max Act: 7.0942. Min Act: -0.1700

Data Index: 4696860 (Open Web Text)

Max Activating Token Index: 467

Text #15

Max Range: 7.3442. Min Range: -7.3442

Max Act: 7.0942. Min Act: -0.1700

Data Index: 3214084 (Open Web Text)

Max Activating Token Index: 197

Text #16

Max Range: 7.3442. Min Range: -7.3442

Max Act: 7.0942. Min Act: -0.1700

Data Index: 1431881 (Open Web Text)

Max Activating Token Index: 875

Text #17

Max Range: 7.3442. Min Range: -7.3442

Max Act: 7.0629. Min Act: -0.1700

Data Index: 4650121 (Open Web Text)

Max Activating Token Index: 839

Text #18

Max Range: 7.3442. Min Range: -7.3442

Max Act: 7.0629. Min Act: -0.1700

Data Index: 5255875 (Open Web Text)

Max Activating Token Index: 636

Text #19

Max Range: 7.3442. Min Range: -7.3442

Max Act: 7.0317. Min Act: -0.1700

Data Index: 1811053 (Open Web Text)

Max Activating Token Index: 468