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

Dataset: Open Web Text

Neuron 1896 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: 3.2977. Min Range: -3.2977

Max Act: 3.2496. Min Act: -0.1700

Data Index: 1297602 (Open Web Text)

Max Activating Token Index: 929

Text #1

Max Range: 3.2977. Min Range: -3.2977

Max Act: 3.2504. Min Act: -0.1700

Data Index: 5691446 (Open Web Text)

Max Activating Token Index: 907

Text #2

Max Range: 3.2977. Min Range: -3.2977

Max Act: 3.2977. Min Act: -0.1700

Data Index: 1426147 (Open Web Text)

Max Activating Token Index: 715

Text #3

Max Range: 3.2977. Min Range: -3.2977

Max Act: 3.2731. Min Act: -0.1700

Data Index: 448691 (Open Web Text)

Max Activating Token Index: 996

Text #4

Max Range: 3.2977. Min Range: -3.2977

Max Act: 3.2288. Min Act: -0.1700

Data Index: 1056562 (Open Web Text)

Max Activating Token Index: 738

Text #5

Max Range: 3.2977. Min Range: -3.2977

Max Act: 3.2086. Min Act: -0.1700

Data Index: 2939041 (Open Web Text)

Max Activating Token Index: 669

Text #6

Max Range: 3.2977. Min Range: -3.2977

Max Act: 3.2192. Min Act: -0.1700

Data Index: 5104207 (Open Web Text)

Max Activating Token Index: 824

Text #7

Max Range: 3.2977. Min Range: -3.2977

Max Act: 3.1984. Min Act: -0.1700

Data Index: 4171917 (Open Web Text)

Max Activating Token Index: 66

Text #8

Max Range: 3.2977. Min Range: -3.2977

Max Act: 3.1785. Min Act: -0.1700

Data Index: 4958525 (Open Web Text)

Max Activating Token Index: 823

Text #9

Max Range: 3.2977. Min Range: -3.2977

Max Act: 3.1692. Min Act: -0.1700

Data Index: 8262499 (Open Web Text)

Max Activating Token Index: 166

Text #10

Max Range: 3.2977. Min Range: -3.2977

Max Act: 3.1633. Min Act: -0.1700

Data Index: 7397241 (Open Web Text)

Max Activating Token Index: 420

Text #11

Max Range: 3.2977. Min Range: -3.2977

Max Act: 3.1867. Min Act: -0.1700

Data Index: 6957634 (Open Web Text)

Max Activating Token Index: 102

Text #12

Max Range: 3.2977. Min Range: -3.2977

Max Act: 3.1226. Min Act: -0.1700

Data Index: 5882296 (Open Web Text)

Max Activating Token Index: 763

Text #13

Max Range: 3.2977. Min Range: -3.2977

Max Act: 3.1444. Min Act: -0.1700

Data Index: 7956984 (Open Web Text)

Max Activating Token Index: 524

Text #14

Max Range: 3.2977. Min Range: -3.2977

Max Act: 3.1067. Min Act: -0.1700

Data Index: 4378262 (Open Web Text)

Max Activating Token Index: 694

Text #15

Max Range: 3.2977. Min Range: -3.2977

Max Act: 3.1178. Min Act: -0.1700

Data Index: 6996625 (Open Web Text)

Max Activating Token Index: 905

Text #16

Max Range: 3.2977. Min Range: -3.2977

Max Act: 3.0935. Min Act: -0.1700

Data Index: 4103102 (Open Web Text)

Max Activating Token Index: 657

Text #17

Max Range: 3.2977. Min Range: -3.2977

Max Act: 3.0787. Min Act: -0.1700

Data Index: 4943038 (Open Web Text)

Max Activating Token Index: 408

Text #18

Max Range: 3.2977. Min Range: -3.2977

Max Act: 3.1304. Min Act: -0.1700

Data Index: 5394957 (Open Web Text)

Max Activating Token Index: 447

Text #19

Max Range: 3.2977. Min Range: -3.2977

Max Act: 3.0986. Min Act: -0.1700

Data Index: 5654804 (Open Web Text)

Max Activating Token Index: 41