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

Dataset: Open Web Text

Neuron 2024 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: 3.5656. Min Range: -3.5656

Max Act: 3.5656. Min Act: -0.1700

Data Index: 8227502 (Open Web Text)

Max Activating Token Index: 13

Text #1

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.5472. Min Act: -0.1700

Data Index: 5319940 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.5295. Min Act: -0.1700

Data Index: 8545066 (Open Web Text)

Max Activating Token Index: 263

Text #3

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.5193. Min Act: -0.1700

Data Index: 4435533 (Open Web Text)

Max Activating Token Index: 792

Text #4

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.4782. Min Act: -0.1700

Data Index: 2523557 (Open Web Text)

Max Activating Token Index: 751

Text #5

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.4805. Min Act: -0.1700

Data Index: 3157206 (Open Web Text)

Max Activating Token Index: 921

Text #6

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.4917. Min Act: -0.1700

Data Index: 5475921 (Open Web Text)

Max Activating Token Index: 17

Text #7

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.4751. Min Act: -0.1700

Data Index: 4266102 (Open Web Text)

Max Activating Token Index: 38

Text #8

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.4607. Min Act: -0.1700

Data Index: 2224534 (Open Web Text)

Max Activating Token Index: 27

Text #9

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.4489. Min Act: -0.1700

Data Index: 6913469 (Open Web Text)

Max Activating Token Index: 58

Text #10

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.4150. Min Act: -0.1700

Data Index: 4879954 (Open Web Text)

Max Activating Token Index: 818

Text #11

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.4145. Min Act: -0.1700

Data Index: 2923150 (Open Web Text)

Max Activating Token Index: 197

Text #12

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.4128. Min Act: -0.1700

Data Index: 868268 (Open Web Text)

Max Activating Token Index: 782

Text #13

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.4200. Min Act: -0.1700

Data Index: 8353300 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.4303. Min Act: -0.1700

Data Index: 2994652 (Open Web Text)

Max Activating Token Index: 111

Text #15

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.4214. Min Act: -0.1700

Data Index: 3534493 (Open Web Text)

Max Activating Token Index: 762

Text #16

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.3953. Min Act: -0.1700

Data Index: 976848 (Open Web Text)

Max Activating Token Index: 703

Text #17

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.3579. Min Act: -0.1700

Data Index: 2614605 (Open Web Text)

Max Activating Token Index: 955

Text #18

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.3836. Min Act: -0.1700

Data Index: 1557867 (Open Web Text)

Max Activating Token Index: 843

Text #19

Max Range: 3.5656. Min Range: -3.5656

Max Act: 3.3828. Min Act: -0.1700

Data Index: 1649738 (Open Web Text)

Max Activating Token Index: 7