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

Dataset: Open Web Text

Neuron 587 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: 5.2233. Min Range: -5.2233

Max Act: 5.2233. Min Act: -0.1700

Data Index: 1205410 (Open Web Text)

Max Activating Token Index: 184

Text #1

Max Range: 5.2233. Min Range: -5.2233

Max Act: 5.2077. Min Act: -0.1700

Data Index: 2474587 (Open Web Text)

Max Activating Token Index: 1016

Text #2

Max Range: 5.2233. Min Range: -5.2233

Max Act: 5.1821. Min Act: -0.1700

Data Index: 2615975 (Open Web Text)

Max Activating Token Index: 976

Text #3

Max Range: 5.2233. Min Range: -5.2233

Max Act: 5.1858. Min Act: -0.1700

Data Index: 911006 (Open Web Text)

Max Activating Token Index: 916

Text #4

Max Range: 5.2233. Min Range: -5.2233

Max Act: 5.1883. Min Act: -0.1700

Data Index: 4620904 (Open Web Text)

Max Activating Token Index: 755

Text #5

Max Range: 5.2233. Min Range: -5.2233

Max Act: 5.0918. Min Act: -0.1700

Data Index: 304042 (Open Web Text)

Max Activating Token Index: 1012

Text #6

Max Range: 5.2233. Min Range: -5.2233

Max Act: 5.0926. Min Act: -0.1700

Data Index: 1008774 (Open Web Text)

Max Activating Token Index: 974

Text #7

Max Range: 5.2233. Min Range: -5.2233

Max Act: 5.1235. Min Act: -0.1700

Data Index: 3362780 (Open Web Text)

Max Activating Token Index: 459

Text #8

Max Range: 5.2233. Min Range: -5.2233

Max Act: 5.0544. Min Act: -0.1700

Data Index: 6914029 (Open Web Text)

Max Activating Token Index: 61

Text #9

Max Range: 5.2233. Min Range: -5.2233

Max Act: 5.0816. Min Act: -0.1700

Data Index: 1439199 (Open Web Text)

Max Activating Token Index: 971

Text #10

Max Range: 5.2233. Min Range: -5.2233

Max Act: 5.0661. Min Act: -0.1700

Data Index: 5885734 (Open Web Text)

Max Activating Token Index: 172

Text #11

Max Range: 5.2233. Min Range: -5.2233

Max Act: 5.1131. Min Act: -0.1700

Data Index: 7818504 (Open Web Text)

Max Activating Token Index: 447

Text #12

Max Range: 5.2233. Min Range: -5.2233

Max Act: 5.0800. Min Act: -0.1700

Data Index: 6045104 (Open Web Text)

Max Activating Token Index: 138

Text #13

Max Range: 5.2233. Min Range: -5.2233

Max Act: 5.0202. Min Act: -0.1700

Data Index: 7019894 (Open Web Text)

Max Activating Token Index: 197

Text #14

Max Range: 5.2233. Min Range: -5.2233

Max Act: 5.0639. Min Act: -0.1700

Data Index: 1387532 (Open Web Text)

Max Activating Token Index: 915

Text #15

Max Range: 5.2233. Min Range: -5.2233

Max Act: 5.0684. Min Act: -0.1700

Data Index: 8374077 (Open Web Text)

Max Activating Token Index: 457

Text #16

Max Range: 5.2233. Min Range: -5.2233

Max Act: 5.0872. Min Act: -0.1700

Data Index: 5929741 (Open Web Text)

Max Activating Token Index: 23

Text #17

Max Range: 5.2233. Min Range: -5.2233

Max Act: 5.0538. Min Act: -0.1700

Data Index: 4795103 (Open Web Text)

Max Activating Token Index: 194

Text #18

Max Range: 5.2233. Min Range: -5.2233

Max Act: 5.0126. Min Act: -0.1700

Data Index: 6657312 (Open Web Text)

Max Activating Token Index: 861

Text #19

Max Range: 5.2233. Min Range: -5.2233

Max Act: 5.0219. Min Act: -0.1700

Data Index: 6612666 (Open Web Text)

Max Activating Token Index: 998