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

Dataset: Open Web Text

Neuron 79 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: 4.8839. Min Range: -4.8839

Max Act: 4.8839. Min Act: -0.1700

Data Index: 453379 (Open Web Text)

Max Activating Token Index: 217

Text #1

Max Range: 4.8839. Min Range: -4.8839

Max Act: 4.7411. Min Act: -0.1700

Data Index: 6298578 (Open Web Text)

Max Activating Token Index: 211

Text #2

Max Range: 4.8839. Min Range: -4.8839

Max Act: 4.7302. Min Act: -0.1700

Data Index: 8446227 (Open Web Text)

Max Activating Token Index: 616

Text #3

Max Range: 4.8839. Min Range: -4.8839

Max Act: 4.7445. Min Act: -0.1700

Data Index: 5816346 (Open Web Text)

Max Activating Token Index: 274

Text #4

Max Range: 4.8839. Min Range: -4.8839

Max Act: 4.6686. Min Act: -0.1700

Data Index: 4219114 (Open Web Text)

Max Activating Token Index: 243

Text #5

Max Range: 4.8839. Min Range: -4.8839

Max Act: 4.7308. Min Act: -0.1700

Data Index: 899476 (Open Web Text)

Max Activating Token Index: 602

Text #6

Max Range: 4.8839. Min Range: -4.8839

Max Act: 4.7018. Min Act: -0.1700

Data Index: 4075434 (Open Web Text)

Max Activating Token Index: 576

Text #7

Max Range: 4.8839. Min Range: -4.8839

Max Act: 4.7304. Min Act: -0.1700

Data Index: 6202997 (Open Web Text)

Max Activating Token Index: 342

Text #8

Max Range: 4.8839. Min Range: -4.8839

Max Act: 4.7181. Min Act: -0.1700

Data Index: 8124610 (Open Web Text)

Max Activating Token Index: 16

Text #9

Max Range: 4.8839. Min Range: -4.8839

Max Act: 4.7029. Min Act: -0.1700

Data Index: 490312 (Open Web Text)

Max Activating Token Index: 433

Text #10

Max Range: 4.8839. Min Range: -4.8839

Max Act: 4.7034. Min Act: -0.1700

Data Index: 3482702 (Open Web Text)

Max Activating Token Index: 638

Text #11

Max Range: 4.8839. Min Range: -4.8839

Max Act: 4.6837. Min Act: -0.1700

Data Index: 7640471 (Open Web Text)

Max Activating Token Index: 192

Text #12

Max Range: 4.8839. Min Range: -4.8839

Max Act: 4.7220. Min Act: -0.1700

Data Index: 1230882 (Open Web Text)

Max Activating Token Index: 797

Text #13

Max Range: 4.8839. Min Range: -4.8839

Max Act: 4.6278. Min Act: -0.1700

Data Index: 503771 (Open Web Text)

Max Activating Token Index: 820

Text #14

Max Range: 4.8839. Min Range: -4.8839

Max Act: 4.7203. Min Act: -0.1700

Data Index: 1254167 (Open Web Text)

Max Activating Token Index: 659

Text #15

Max Range: 4.8839. Min Range: -4.8839

Max Act: 4.6670. Min Act: -0.1700

Data Index: 1261043 (Open Web Text)

Max Activating Token Index: 897

Text #16

Max Range: 4.8839. Min Range: -4.8839

Max Act: 4.6614. Min Act: -0.1700

Data Index: 7678802 (Open Web Text)

Max Activating Token Index: 52

Text #17

Max Range: 4.8839. Min Range: -4.8839

Max Act: 4.6570. Min Act: -0.1700

Data Index: 1280645 (Open Web Text)

Max Activating Token Index: 473

Text #18

Max Range: 4.8839. Min Range: -4.8839

Max Act: 4.7092. Min Act: -0.1700

Data Index: 7381687 (Open Web Text)

Max Activating Token Index: 29

Text #19

Max Range: 4.8839. Min Range: -4.8839

Max Act: 4.6769. Min Act: -0.1700

Data Index: 6565820 (Open Web Text)

Max Activating Token Index: 418