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

Dataset: Open Web Text

Neuron 1088 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: 4.8690. Min Range: -4.8690

Max Act: 4.8690. Min Act: -0.1700

Data Index: 2885152 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.8316. Min Act: -0.1700

Data Index: 6421671 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.7500. Min Act: -0.1700

Data Index: 5950934 (Open Web Text)

Max Activating Token Index: 69

Text #3

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.7208. Min Act: -0.1700

Data Index: 8110927 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.6810. Min Act: -0.1700

Data Index: 8269995 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.6631. Min Act: -0.1700

Data Index: 3612209 (Open Web Text)

Max Activating Token Index: 182

Text #6

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.6994. Min Act: -0.1700

Data Index: 7824619 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.6423. Min Act: -0.1700

Data Index: 1570707 (Open Web Text)

Max Activating Token Index: 15

Text #8

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.6434. Min Act: -0.1700

Data Index: 5673790 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.6533. Min Act: -0.1700

Data Index: 4859754 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.6049. Min Act: -0.1700

Data Index: 8621964 (Open Web Text)

Max Activating Token Index: 30

Text #11

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.6291. Min Act: -0.1700

Data Index: 1888226 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.5842. Min Act: -0.1700

Data Index: 677899 (Open Web Text)

Max Activating Token Index: 355

Text #13

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.6010. Min Act: -0.1700

Data Index: 5571731 (Open Web Text)

Max Activating Token Index: 121

Text #14

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.5933. Min Act: -0.1700

Data Index: 1518095 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.6014. Min Act: -0.1700

Data Index: 397416 (Open Web Text)

Max Activating Token Index: 354

Text #16

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.5746. Min Act: -0.1700

Data Index: 4605553 (Open Web Text)

Max Activating Token Index: 22

Text #17

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.5727. Min Act: -0.1700

Data Index: 4003604 (Open Web Text)

Max Activating Token Index: 56

Text #18

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.5778. Min Act: -0.1700

Data Index: 3878493 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 4.8690. Min Range: -4.8690

Max Act: 4.5383. Min Act: -0.1700

Data Index: 3201233 (Open Web Text)

Max Activating Token Index: 34