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

Dataset: Open Web Text

Neuron 2545 in Layer 2

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: 3.1720. Min Range: -3.1720

Max Act: 3.1720. Min Act: -0.1700

Data Index: 8571657 (Open Web Text)

Max Activating Token Index: 916

Text #1

Max Range: 3.1720. Min Range: -3.1720

Max Act: 3.1512. Min Act: -0.1700

Data Index: 6913826 (Open Web Text)

Max Activating Token Index: 268

Text #2

Max Range: 3.1720. Min Range: -3.1720

Max Act: 3.1224. Min Act: -0.1700

Data Index: 5391439 (Open Web Text)

Max Activating Token Index: 853

Text #3

Max Range: 3.1720. Min Range: -3.1720

Max Act: 3.1098. Min Act: -0.1700

Data Index: 472333 (Open Web Text)

Max Activating Token Index: 106

Text #4

Max Range: 3.1720. Min Range: -3.1720

Max Act: 3.0649. Min Act: -0.1700

Data Index: 8111347 (Open Web Text)

Max Activating Token Index: 907

Text #5

Max Range: 3.1720. Min Range: -3.1720

Max Act: 3.0490. Min Act: -0.1700

Data Index: 6216315 (Open Web Text)

Max Activating Token Index: 561

Text #6

Max Range: 3.1720. Min Range: -3.1720

Max Act: 3.0514. Min Act: -0.1700

Data Index: 4146640 (Open Web Text)

Max Activating Token Index: 504

Text #7

Max Range: 3.1720. Min Range: -3.1720

Max Act: 3.0426. Min Act: -0.1700

Data Index: 7489516 (Open Web Text)

Max Activating Token Index: 227

Text #8

Max Range: 3.1720. Min Range: -3.1720

Max Act: 3.0004. Min Act: -0.1700

Data Index: 7634327 (Open Web Text)

Max Activating Token Index: 792

Text #9

Max Range: 3.1720. Min Range: -3.1720

Max Act: 2.9934. Min Act: -0.1700

Data Index: 111358 (Open Web Text)

Max Activating Token Index: 578

Text #10

Max Range: 3.1720. Min Range: -3.1720

Max Act: 3.0058. Min Act: -0.1700

Data Index: 4567069 (Open Web Text)

Max Activating Token Index: 232

Text #11

Max Range: 3.1720. Min Range: -3.1720

Max Act: 2.9837. Min Act: -0.1700

Data Index: 7074546 (Open Web Text)

Max Activating Token Index: 356

Text #12

Max Range: 3.1720. Min Range: -3.1720

Max Act: 2.9706. Min Act: -0.1700

Data Index: 4147146 (Open Web Text)

Max Activating Token Index: 855

Text #13

Max Range: 3.1720. Min Range: -3.1720

Max Act: 2.9737. Min Act: -0.1700

Data Index: 5992772 (Open Web Text)

Max Activating Token Index: 287

Text #14

Max Range: 3.1720. Min Range: -3.1720

Max Act: 2.9742. Min Act: -0.1700

Data Index: 2460709 (Open Web Text)

Max Activating Token Index: 432

Text #15

Max Range: 3.1720. Min Range: -3.1720

Max Act: 2.9750. Min Act: -0.1700

Data Index: 1196024 (Open Web Text)

Max Activating Token Index: 524

Text #16

Max Range: 3.1720. Min Range: -3.1720

Max Act: 2.9335. Min Act: -0.1700

Data Index: 3880911 (Open Web Text)

Max Activating Token Index: 384

Text #17

Max Range: 3.1720. Min Range: -3.1720

Max Act: 2.9438. Min Act: -0.1700

Data Index: 8547467 (Open Web Text)

Max Activating Token Index: 423

Text #18

Max Range: 3.1720. Min Range: -3.1720

Max Act: 2.9325. Min Act: -0.1700

Data Index: 664448 (Open Web Text)

Max Activating Token Index: 677

Text #19

Max Range: 3.1720. Min Range: -3.1720

Max Act: 2.9159. Min Act: -0.1700

Data Index: 1928171 (Open Web Text)

Max Activating Token Index: 796