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

Dataset: Open Web Text

Neuron 461 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: 1.8017. Min Range: -1.8017

Max Act: 1.8017. Min Act: -0.1700

Data Index: 3534243 (Open Web Text)

Max Activating Token Index: 559

Text #1

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.7395. Min Act: -0.1700

Data Index: 1826175 (Open Web Text)

Max Activating Token Index: 884

Text #2

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.7186. Min Act: -0.1700

Data Index: 6027995 (Open Web Text)

Max Activating Token Index: 931

Text #3

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.7220. Min Act: -0.1700

Data Index: 8528444 (Open Web Text)

Max Activating Token Index: 606

Text #4

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.7388. Min Act: -0.1700

Data Index: 4028929 (Open Web Text)

Max Activating Token Index: 656

Text #5

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.7248. Min Act: -0.1700

Data Index: 871463 (Open Web Text)

Max Activating Token Index: 92

Text #6

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.7218. Min Act: -0.1700

Data Index: 8092906 (Open Web Text)

Max Activating Token Index: 187

Text #7

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.7043. Min Act: -0.1700

Data Index: 560973 (Open Web Text)

Max Activating Token Index: 626

Text #8

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.7098. Min Act: -0.1700

Data Index: 7636787 (Open Web Text)

Max Activating Token Index: 485

Text #9

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.7152. Min Act: -0.1700

Data Index: 2185745 (Open Web Text)

Max Activating Token Index: 587

Text #10

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.7071. Min Act: -0.1700

Data Index: 5424496 (Open Web Text)

Max Activating Token Index: 407

Text #11

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.7080. Min Act: -0.1700

Data Index: 1937213 (Open Web Text)

Max Activating Token Index: 66

Text #12

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.7147. Min Act: -0.1700

Data Index: 2498894 (Open Web Text)

Max Activating Token Index: 1017

Text #13

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.6966. Min Act: -0.1700

Data Index: 6679142 (Open Web Text)

Max Activating Token Index: 454

Text #14

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.6922. Min Act: -0.1700

Data Index: 8618384 (Open Web Text)

Max Activating Token Index: 70

Text #15

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.6994. Min Act: -0.1700

Data Index: 774983 (Open Web Text)

Max Activating Token Index: 175

Text #16

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.7055. Min Act: -0.1700

Data Index: 8627935 (Open Web Text)

Max Activating Token Index: 640

Text #17

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.6953. Min Act: -0.1700

Data Index: 2187488 (Open Web Text)

Max Activating Token Index: 302

Text #18

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.6579. Min Act: -0.1700

Data Index: 5575145 (Open Web Text)

Max Activating Token Index: 645

Text #19

Max Range: 1.8017. Min Range: -1.8017

Max Act: 1.6813. Min Act: -0.1700

Data Index: 1301708 (Open Web Text)

Max Activating Token Index: 379