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

Dataset: Open Web Text

Neuron 452 in Layer 3

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: 2.9216. Min Range: -2.9216

Max Act: 2.9216. Min Act: -0.1700

Data Index: 7238222 (Open Web Text)

Max Activating Token Index: 408

Text #1

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.8561. Min Act: -0.1700

Data Index: 4944891 (Open Web Text)

Max Activating Token Index: 15

Text #2

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.8567. Min Act: -0.1700

Data Index: 2344586 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.8193. Min Act: -0.1700

Data Index: 5977288 (Open Web Text)

Max Activating Token Index: 154

Text #4

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.8103. Min Act: -0.1700

Data Index: 1699060 (Open Web Text)

Max Activating Token Index: 230

Text #5

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.7724. Min Act: -0.1700

Data Index: 7618213 (Open Web Text)

Max Activating Token Index: 467

Text #6

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.7447. Min Act: -0.1700

Data Index: 1849846 (Open Web Text)

Max Activating Token Index: 247

Text #7

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.6870. Min Act: -0.1700

Data Index: 221968 (Open Web Text)

Max Activating Token Index: 1021

Text #8

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.7444. Min Act: -0.1700

Data Index: 7618214 (Open Web Text)

Max Activating Token Index: 826

Text #9

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.7402. Min Act: -0.1700

Data Index: 1126787 (Open Web Text)

Max Activating Token Index: 787

Text #10

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.7460. Min Act: -0.1700

Data Index: 6683342 (Open Web Text)

Max Activating Token Index: 535

Text #11

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.7719. Min Act: -0.1700

Data Index: 6369739 (Open Web Text)

Max Activating Token Index: 480

Text #12

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.7107. Min Act: -0.1700

Data Index: 6292747 (Open Web Text)

Max Activating Token Index: 348

Text #13

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.7212. Min Act: -0.1700

Data Index: 224557 (Open Web Text)

Max Activating Token Index: 995

Text #14

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.7167. Min Act: -0.1700

Data Index: 6292746 (Open Web Text)

Max Activating Token Index: 48

Text #15

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.7157. Min Act: -0.1700

Data Index: 3025361 (Open Web Text)

Max Activating Token Index: 343

Text #16

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.6874. Min Act: -0.1700

Data Index: 3304330 (Open Web Text)

Max Activating Token Index: 833

Text #17

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.7683. Min Act: -0.1700

Data Index: 814433 (Open Web Text)

Max Activating Token Index: 768

Text #18

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.7322. Min Act: -0.1700

Data Index: 1766303 (Open Web Text)

Max Activating Token Index: 217

Text #19

Max Range: 2.9216. Min Range: -2.9216

Max Act: 2.7237. Min Act: -0.1700

Data Index: 7367359 (Open Web Text)

Max Activating Token Index: 154