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

Dataset: Open Web Text

Neuron 1720 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: 4.5478. Min Range: -4.5478

Max Act: 4.5478. Min Act: -0.1700

Data Index: 7264661 (Open Web Text)

Max Activating Token Index: 193

Text #1

Max Range: 4.5478. Min Range: -4.5478

Max Act: 4.4785. Min Act: -0.1700

Data Index: 5008562 (Open Web Text)

Max Activating Token Index: 236

Text #2

Max Range: 4.5478. Min Range: -4.5478

Max Act: 4.2268. Min Act: -0.1700

Data Index: 987522 (Open Web Text)

Max Activating Token Index: 154

Text #3

Max Range: 4.5478. Min Range: -4.5478

Max Act: 4.2247. Min Act: -0.1700

Data Index: 7542843 (Open Web Text)

Max Activating Token Index: 852

Text #4

Max Range: 4.5478. Min Range: -4.5478

Max Act: 4.2341. Min Act: -0.1700

Data Index: 5028228 (Open Web Text)

Max Activating Token Index: 727

Text #5

Max Range: 4.5478. Min Range: -4.5478

Max Act: 4.1585. Min Act: -0.1700

Data Index: 6161614 (Open Web Text)

Max Activating Token Index: 235

Text #6

Max Range: 4.5478. Min Range: -4.5478

Max Act: 4.1679. Min Act: -0.1700

Data Index: 6909371 (Open Web Text)

Max Activating Token Index: 350

Text #7

Max Range: 4.5478. Min Range: -4.5478

Max Act: 4.1331. Min Act: -0.1700

Data Index: 1337142 (Open Web Text)

Max Activating Token Index: 32

Text #8

Max Range: 4.5478. Min Range: -4.5478

Max Act: 4.0989. Min Act: -0.1700

Data Index: 8738848 (Open Web Text)

Max Activating Token Index: 52

Text #9

Max Range: 4.5478. Min Range: -4.5478

Max Act: 4.1284. Min Act: -0.1700

Data Index: 471677 (Open Web Text)

Max Activating Token Index: 467

Text #10

Max Range: 4.5478. Min Range: -4.5478

Max Act: 4.1237. Min Act: -0.1700

Data Index: 4659973 (Open Web Text)

Max Activating Token Index: 752

Text #11

Max Range: 4.5478. Min Range: -4.5478

Max Act: 4.0839. Min Act: -0.1700

Data Index: 8613068 (Open Web Text)

Max Activating Token Index: 274

Text #12

Max Range: 4.5478. Min Range: -4.5478

Max Act: 4.0802. Min Act: -0.1700

Data Index: 6647568 (Open Web Text)

Max Activating Token Index: 210

Text #13

Max Range: 4.5478. Min Range: -4.5478

Max Act: 4.0906. Min Act: -0.1700

Data Index: 6654846 (Open Web Text)

Max Activating Token Index: 679

Text #14

Max Range: 4.5478. Min Range: -4.5478

Max Act: 4.0315. Min Act: -0.1700

Data Index: 7105165 (Open Web Text)

Max Activating Token Index: 951

Text #15

Max Range: 4.5478. Min Range: -4.5478

Max Act: 4.0423. Min Act: -0.1700

Data Index: 5679223 (Open Web Text)

Max Activating Token Index: 121

Text #16

Max Range: 4.5478. Min Range: -4.5478

Max Act: 4.0117. Min Act: -0.1700

Data Index: 3862290 (Open Web Text)

Max Activating Token Index: 78

Text #17

Max Range: 4.5478. Min Range: -4.5478

Max Act: 4.0277. Min Act: -0.1700

Data Index: 7748843 (Open Web Text)

Max Activating Token Index: 407

Text #18

Max Range: 4.5478. Min Range: -4.5478

Max Act: 4.0309. Min Act: -0.1700

Data Index: 7569256 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 4.5478. Min Range: -4.5478

Max Act: 4.0071. Min Act: -0.1700

Data Index: 7951532 (Open Web Text)

Max Activating Token Index: 211