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

Dataset: Open Web Text

Neuron 1724 in Layer 5

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: 4.8898. Min Range: -4.8898

Max Act: 4.8898. Min Act: -0.1700

Data Index: 7226289 (Open Web Text)

Max Activating Token Index: 1017

Text #1

Max Range: 4.8898. Min Range: -4.8898

Max Act: 4.8794. Min Act: -0.1700

Data Index: 1465429 (Open Web Text)

Max Activating Token Index: 14

Text #2

Max Range: 4.8898. Min Range: -4.8898

Max Act: 4.8436. Min Act: -0.1700

Data Index: 5100566 (Open Web Text)

Max Activating Token Index: 978

Text #3

Max Range: 4.8898. Min Range: -4.8898

Max Act: 4.8728. Min Act: -0.1700

Data Index: 241271 (Open Web Text)

Max Activating Token Index: 945

Text #4

Max Range: 4.8898. Min Range: -4.8898

Max Act: 4.8579. Min Act: -0.1700

Data Index: 6141096 (Open Web Text)

Max Activating Token Index: 236

Text #5

Max Range: 4.8898. Min Range: -4.8898

Max Act: 4.8415. Min Act: -0.1700

Data Index: 1211205 (Open Web Text)

Max Activating Token Index: 260

Text #6

Max Range: 4.8898. Min Range: -4.8898

Max Act: 4.8392. Min Act: -0.1700

Data Index: 6786759 (Open Web Text)

Max Activating Token Index: 360

Text #7

Max Range: 4.8898. Min Range: -4.8898

Max Act: 4.8139. Min Act: -0.1700

Data Index: 4597805 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 4.8898. Min Range: -4.8898

Max Act: 4.8192. Min Act: -0.1700

Data Index: 2197477 (Open Web Text)

Max Activating Token Index: 608

Text #9

Max Range: 4.8898. Min Range: -4.8898

Max Act: 4.8077. Min Act: -0.1700

Data Index: 530814 (Open Web Text)

Max Activating Token Index: 114

Text #10

Max Range: 4.8898. Min Range: -4.8898

Max Act: 4.8119. Min Act: -0.1700

Data Index: 3360121 (Open Web Text)

Max Activating Token Index: 248

Text #11

Max Range: 4.8898. Min Range: -4.8898

Max Act: 4.8321. Min Act: -0.1700

Data Index: 3323729 (Open Web Text)

Max Activating Token Index: 276

Text #12

Max Range: 4.8898. Min Range: -4.8898

Max Act: 4.8175. Min Act: -0.1700

Data Index: 6325506 (Open Web Text)

Max Activating Token Index: 590

Text #13

Max Range: 4.8898. Min Range: -4.8898

Max Act: 4.7887. Min Act: -0.1700

Data Index: 1577753 (Open Web Text)

Max Activating Token Index: 367

Text #14

Max Range: 4.8898. Min Range: -4.8898

Max Act: 4.7645. Min Act: -0.1700

Data Index: 4579476 (Open Web Text)

Max Activating Token Index: 173

Text #15

Max Range: 4.8898. Min Range: -4.8898

Max Act: 4.7585. Min Act: -0.1700

Data Index: 6658421 (Open Web Text)

Max Activating Token Index: 940

Text #16

Max Range: 4.8898. Min Range: -4.8898

Max Act: 4.7957. Min Act: -0.1700

Data Index: 1195739 (Open Web Text)

Max Activating Token Index: 173

Text #17

Max Range: 4.8898. Min Range: -4.8898

Max Act: 4.7844. Min Act: -0.1700

Data Index: 3921408 (Open Web Text)

Max Activating Token Index: 338

Text #18

Max Range: 4.8898. Min Range: -4.8898

Max Act: 4.7901. Min Act: -0.1700

Data Index: 1113337 (Open Web Text)

Max Activating Token Index: 523

Text #19

Max Range: 4.8898. Min Range: -4.8898

Max Act: 4.7731. Min Act: -0.1700

Data Index: 8242272 (Open Web Text)

Max Activating Token Index: 105