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

Dataset: Open Web Text

Neuron 2145 in Layer 4

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: 3.7534. Min Range: -3.7534

Max Act: 3.7534. Min Act: -0.1700

Data Index: 8557235 (Open Web Text)

Max Activating Token Index: 843

Text #1

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.5457. Min Act: -0.1700

Data Index: 6479449 (Open Web Text)

Max Activating Token Index: 234

Text #2

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.4937. Min Act: -0.1700

Data Index: 5572956 (Open Web Text)

Max Activating Token Index: 19

Text #3

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.4906. Min Act: -0.1700

Data Index: 6314032 (Open Web Text)

Max Activating Token Index: 83

Text #4

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.4844. Min Act: -0.1700

Data Index: 7774236 (Open Web Text)

Max Activating Token Index: 245

Text #5

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.4948. Min Act: -0.1700

Data Index: 2783869 (Open Web Text)

Max Activating Token Index: 260

Text #6

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.4843. Min Act: -0.1700

Data Index: 5414747 (Open Web Text)

Max Activating Token Index: 841

Text #7

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.4626. Min Act: -0.1700

Data Index: 5075844 (Open Web Text)

Max Activating Token Index: 623

Text #8

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.4285. Min Act: -0.1700

Data Index: 6790905 (Open Web Text)

Max Activating Token Index: 652

Text #9

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.4355. Min Act: -0.1700

Data Index: 3284468 (Open Web Text)

Max Activating Token Index: 96

Text #10

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.4278. Min Act: -0.1700

Data Index: 5562652 (Open Web Text)

Max Activating Token Index: 145

Text #11

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.4187. Min Act: -0.1700

Data Index: 4561752 (Open Web Text)

Max Activating Token Index: 428

Text #12

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.4246. Min Act: -0.1700

Data Index: 7433987 (Open Web Text)

Max Activating Token Index: 197

Text #13

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.3921. Min Act: -0.1700

Data Index: 7707329 (Open Web Text)

Max Activating Token Index: 273

Text #14

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.4144. Min Act: -0.1700

Data Index: 5445271 (Open Web Text)

Max Activating Token Index: 1003

Text #15

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.4156. Min Act: -0.1700

Data Index: 4004050 (Open Web Text)

Max Activating Token Index: 601

Text #16

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.4055. Min Act: -0.1700

Data Index: 8304513 (Open Web Text)

Max Activating Token Index: 671

Text #17

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.4015. Min Act: -0.1700

Data Index: 337390 (Open Web Text)

Max Activating Token Index: 687

Text #18

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.4010. Min Act: -0.1700

Data Index: 1484448 (Open Web Text)

Max Activating Token Index: 963

Text #19

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.4051. Min Act: -0.1700

Data Index: 4119812 (Open Web Text)

Max Activating Token Index: 575