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

Dataset: Open Web Text

Neuron 831 in Layer 0

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: 4.2357. Min Range: -4.2357

Max Act: 4.2357. Min Act: -0.1700

Data Index: 5117274 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.2357. Min Range: -4.2357

Max Act: 4.1859. Min Act: -0.1700

Data Index: 2105772 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.2357. Min Range: -4.2357

Max Act: 4.1045. Min Act: -0.1700

Data Index: 8454759 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.2357. Min Range: -4.2357

Max Act: 4.1233. Min Act: -0.1700

Data Index: 2057564 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.2357. Min Range: -4.2357

Max Act: 4.1242. Min Act: -0.1700

Data Index: 7456703 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 4.2357. Min Range: -4.2357

Max Act: 4.1091. Min Act: -0.1700

Data Index: 6863795 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 4.2357. Min Range: -4.2357

Max Act: 4.0720. Min Act: -0.1700

Data Index: 3612623 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.2357. Min Range: -4.2357

Max Act: 4.0953. Min Act: -0.1700

Data Index: 1561858 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.2357. Min Range: -4.2357

Max Act: 4.0743. Min Act: -0.1700

Data Index: 6762395 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.2357. Min Range: -4.2357

Max Act: 4.0671. Min Act: -0.1700

Data Index: 4814243 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 4.2357. Min Range: -4.2357

Max Act: 4.0730. Min Act: -0.1700

Data Index: 8018894 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.2357. Min Range: -4.2357

Max Act: 4.0512. Min Act: -0.1700

Data Index: 8116029 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 4.2357. Min Range: -4.2357

Max Act: 4.0445. Min Act: -0.1700

Data Index: 4611335 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 4.2357. Min Range: -4.2357

Max Act: 4.0667. Min Act: -0.1700

Data Index: 6164807 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 4.2357. Min Range: -4.2357

Max Act: 4.0587. Min Act: -0.1700

Data Index: 5602320 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.2357. Min Range: -4.2357

Max Act: 4.0585. Min Act: -0.1700

Data Index: 2144194 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 4.2357. Min Range: -4.2357

Max Act: 4.0639. Min Act: -0.1700

Data Index: 7705459 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.2357. Min Range: -4.2357

Max Act: 4.0638. Min Act: -0.1700

Data Index: 4378799 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 4.2357. Min Range: -4.2357

Max Act: 4.0615. Min Act: -0.1700

Data Index: 5349333 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 4.2357. Min Range: -4.2357

Max Act: 4.0739. Min Act: -0.1700

Data Index: 3978276 (Open Web Text)

Max Activating Token Index: 3