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

Dataset: Open Web Text

Neuron 1539 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: 4.6169. Min Range: -4.6169

Max Act: 4.6169. Min Act: -0.1700

Data Index: 6230445 (Open Web Text)

Max Activating Token Index: 62

Text #1

Max Range: 4.6169. Min Range: -4.6169

Max Act: 4.5865. Min Act: -0.1700

Data Index: 447755 (Open Web Text)

Max Activating Token Index: 29

Text #2

Max Range: 4.6169. Min Range: -4.6169

Max Act: 4.4805. Min Act: -0.1700

Data Index: 5827440 (Open Web Text)

Max Activating Token Index: 26

Text #3

Max Range: 4.6169. Min Range: -4.6169

Max Act: 4.5081. Min Act: -0.1700

Data Index: 807874 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 4.6169. Min Range: -4.6169

Max Act: 4.4780. Min Act: -0.1700

Data Index: 7677280 (Open Web Text)

Max Activating Token Index: 32

Text #5

Max Range: 4.6169. Min Range: -4.6169

Max Act: 4.4658. Min Act: -0.1700

Data Index: 5728502 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 4.6169. Min Range: -4.6169

Max Act: 4.4714. Min Act: -0.1700

Data Index: 473463 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 4.6169. Min Range: -4.6169

Max Act: 4.4529. Min Act: -0.1700

Data Index: 5001383 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.6169. Min Range: -4.6169

Max Act: 4.4205. Min Act: -0.1700

Data Index: 4838055 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 4.6169. Min Range: -4.6169

Max Act: 4.4306. Min Act: -0.1700

Data Index: 7677279 (Open Web Text)

Max Activating Token Index: 15

Text #10

Max Range: 4.6169. Min Range: -4.6169

Max Act: 4.4549. Min Act: -0.1700

Data Index: 1264311 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.6169. Min Range: -4.6169

Max Act: 4.4567. Min Act: -0.1700

Data Index: 7334465 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 4.6169. Min Range: -4.6169

Max Act: 4.4217. Min Act: -0.1700

Data Index: 6225865 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.6169. Min Range: -4.6169

Max Act: 4.4248. Min Act: -0.1700

Data Index: 6780045 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 4.6169. Min Range: -4.6169

Max Act: 4.4076. Min Act: -0.1700

Data Index: 8107185 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.6169. Min Range: -4.6169

Max Act: 4.3927. Min Act: -0.1700

Data Index: 6494027 (Open Web Text)

Max Activating Token Index: 712

Text #16

Max Range: 4.6169. Min Range: -4.6169

Max Act: 4.3778. Min Act: -0.1700

Data Index: 361414 (Open Web Text)

Max Activating Token Index: 411

Text #17

Max Range: 4.6169. Min Range: -4.6169

Max Act: 4.3707. Min Act: -0.1700

Data Index: 1030286 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.6169. Min Range: -4.6169

Max Act: 4.3936. Min Act: -0.1700

Data Index: 5779069 (Open Web Text)

Max Activating Token Index: 33

Text #19

Max Range: 4.6169. Min Range: -4.6169

Max Act: 4.3858. Min Act: -0.1700

Data Index: 587394 (Open Web Text)

Max Activating Token Index: 13