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

Dataset: Open Web Text

Neuron 1068 in Layer 1

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: 2.0368. Min Range: -2.0368

Max Act: 2.0195. Min Act: -0.1700

Data Index: 4802833 (Open Web Text)

Max Activating Token Index: 63

Text #1

Max Range: 2.0368. Min Range: -2.0368

Max Act: 2.0368. Min Act: -0.1699

Data Index: 5269943 (Open Web Text)

Max Activating Token Index: 726

Text #2

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.9812. Min Act: -0.1700

Data Index: 607366 (Open Web Text)

Max Activating Token Index: 78

Text #3

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.9578. Min Act: -0.1700

Data Index: 1131702 (Open Web Text)

Max Activating Token Index: 13

Text #4

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.9553. Min Act: -0.1700

Data Index: 6709772 (Open Web Text)

Max Activating Token Index: 419

Text #5

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.9670. Min Act: -0.1700

Data Index: 5312989 (Open Web Text)

Max Activating Token Index: 32

Text #6

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.9300. Min Act: -0.1700

Data Index: 1188302 (Open Web Text)

Max Activating Token Index: 280

Text #7

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.9247. Min Act: -0.1699

Data Index: 3193807 (Open Web Text)

Max Activating Token Index: 504

Text #8

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.9218. Min Act: -0.1700

Data Index: 858462 (Open Web Text)

Max Activating Token Index: 22

Text #9

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.9287. Min Act: -0.1700

Data Index: 3815706 (Open Web Text)

Max Activating Token Index: 15

Text #10

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.9142. Min Act: -0.1700

Data Index: 5578607 (Open Web Text)

Max Activating Token Index: 441

Text #11

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.9159. Min Act: -0.1700

Data Index: 4671711 (Open Web Text)

Max Activating Token Index: 13

Text #12

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.9183. Min Act: -0.1700

Data Index: 94679 (Open Web Text)

Max Activating Token Index: 254

Text #13

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.9152. Min Act: -0.1700

Data Index: 962739 (Open Web Text)

Max Activating Token Index: 831

Text #14

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.9105. Min Act: -0.1700

Data Index: 7552958 (Open Web Text)

Max Activating Token Index: 630

Text #15

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.9052. Min Act: -0.1700

Data Index: 1859262 (Open Web Text)

Max Activating Token Index: 439

Text #16

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.9145. Min Act: -0.1700

Data Index: 5849456 (Open Web Text)

Max Activating Token Index: 409

Text #17

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.9092. Min Act: -0.1700

Data Index: 6188407 (Open Web Text)

Max Activating Token Index: 485

Text #18

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.9074. Min Act: -0.1700

Data Index: 1641797 (Open Web Text)

Max Activating Token Index: 426

Text #19

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.8788. Min Act: -0.1700

Data Index: 2707920 (Open Web Text)

Max Activating Token Index: 699