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

Dataset: Open Web Text

Neuron 771 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: 3.6742. Min Range: -3.6742

Max Act: 3.6742. Min Act: -0.1700

Data Index: 4948009 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.6742. Min Range: -3.6742

Max Act: 3.5313. Min Act: -0.1700

Data Index: 8360409 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.6742. Min Range: -3.6742

Max Act: 3.5220. Min Act: -0.1700

Data Index: 7705186 (Open Web Text)

Max Activating Token Index: 19

Text #3

Max Range: 3.6742. Min Range: -3.6742

Max Act: 3.5050. Min Act: -0.1700

Data Index: 4258790 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.6742. Min Range: -3.6742

Max Act: 3.4898. Min Act: -0.1700

Data Index: 7049723 (Open Web Text)

Max Activating Token Index: 19

Text #5

Max Range: 3.6742. Min Range: -3.6742

Max Act: 3.5034. Min Act: -0.1700

Data Index: 1129698 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.6742. Min Range: -3.6742

Max Act: 3.4711. Min Act: -0.1700

Data Index: 2433407 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.6742. Min Range: -3.6742

Max Act: 3.4648. Min Act: -0.1700

Data Index: 3868091 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.6742. Min Range: -3.6742

Max Act: 3.4552. Min Act: -0.1700

Data Index: 1908524 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 3.6742. Min Range: -3.6742

Max Act: 3.4300. Min Act: -0.1700

Data Index: 6216635 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.6742. Min Range: -3.6742

Max Act: 3.4279. Min Act: -0.1700

Data Index: 2711376 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 3.6742. Min Range: -3.6742

Max Act: 3.4294. Min Act: -0.1700

Data Index: 2817682 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.6742. Min Range: -3.6742

Max Act: 3.4300. Min Act: -0.1700

Data Index: 3211699 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.6742. Min Range: -3.6742

Max Act: 3.4351. Min Act: -0.1700

Data Index: 1174208 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 3.6742. Min Range: -3.6742

Max Act: 3.4549. Min Act: -0.1700

Data Index: 15186 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 3.6742. Min Range: -3.6742

Max Act: 3.4378. Min Act: -0.1700

Data Index: 6603488 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.6742. Min Range: -3.6742

Max Act: 3.4301. Min Act: -0.1700

Data Index: 5997831 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 3.6742. Min Range: -3.6742

Max Act: 3.4467. Min Act: -0.1700

Data Index: 2399388 (Open Web Text)

Max Activating Token Index: 13

Text #18

Max Range: 3.6742. Min Range: -3.6742

Max Act: 3.4519. Min Act: -0.1700

Data Index: 520454 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 3.6742. Min Range: -3.6742

Max Act: 3.4416. Min Act: -0.1700

Data Index: 5954715 (Open Web Text)

Max Activating Token Index: 4