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

Dataset: Open Web Text

Neuron 1918 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: 4.7442. Min Range: -4.7442

Max Act: 4.7442. Min Act: -0.1700

Data Index: 2112952 (Open Web Text)

Max Activating Token Index: 495

Text #1

Max Range: 4.7442. Min Range: -4.7442

Max Act: 4.7374. Min Act: -0.1700

Data Index: 6373590 (Open Web Text)

Max Activating Token Index: 120

Text #2

Max Range: 4.7442. Min Range: -4.7442

Max Act: 4.6321. Min Act: -0.1700

Data Index: 3688439 (Open Web Text)

Max Activating Token Index: 433

Text #3

Max Range: 4.7442. Min Range: -4.7442

Max Act: 4.5984. Min Act: -0.1700

Data Index: 6686493 (Open Web Text)

Max Activating Token Index: 235

Text #4

Max Range: 4.7442. Min Range: -4.7442

Max Act: 4.5819. Min Act: -0.1700

Data Index: 6513719 (Open Web Text)

Max Activating Token Index: 356

Text #5

Max Range: 4.7442. Min Range: -4.7442

Max Act: 4.5830. Min Act: -0.1700

Data Index: 2190812 (Open Web Text)

Max Activating Token Index: 473

Text #6

Max Range: 4.7442. Min Range: -4.7442

Max Act: 4.5361. Min Act: -0.1700

Data Index: 809895 (Open Web Text)

Max Activating Token Index: 705

Text #7

Max Range: 4.7442. Min Range: -4.7442

Max Act: 4.5584. Min Act: -0.1700

Data Index: 6557370 (Open Web Text)

Max Activating Token Index: 223

Text #8

Max Range: 4.7442. Min Range: -4.7442

Max Act: 4.5015. Min Act: -0.1700

Data Index: 8751425 (Open Web Text)

Max Activating Token Index: 37

Text #9

Max Range: 4.7442. Min Range: -4.7442

Max Act: 4.5365. Min Act: -0.1700

Data Index: 8157815 (Open Web Text)

Max Activating Token Index: 514

Text #10

Max Range: 4.7442. Min Range: -4.7442

Max Act: 4.5355. Min Act: -0.1700

Data Index: 1281449 (Open Web Text)

Max Activating Token Index: 241

Text #11

Max Range: 4.7442. Min Range: -4.7442

Max Act: 4.4776. Min Act: -0.1700

Data Index: 7643044 (Open Web Text)

Max Activating Token Index: 455

Text #12

Max Range: 4.7442. Min Range: -4.7442

Max Act: 4.5030. Min Act: -0.1700

Data Index: 1005004 (Open Web Text)

Max Activating Token Index: 76

Text #13

Max Range: 4.7442. Min Range: -4.7442

Max Act: 4.5209. Min Act: -0.1700

Data Index: 3251901 (Open Web Text)

Max Activating Token Index: 364

Text #14

Max Range: 4.7442. Min Range: -4.7442

Max Act: 4.4928. Min Act: -0.1700

Data Index: 4946640 (Open Web Text)

Max Activating Token Index: 967

Text #15

Max Range: 4.7442. Min Range: -4.7442

Max Act: 4.5187. Min Act: -0.1700

Data Index: 973895 (Open Web Text)

Max Activating Token Index: 649

Text #16

Max Range: 4.7442. Min Range: -4.7442

Max Act: 4.4715. Min Act: -0.1700

Data Index: 6656735 (Open Web Text)

Max Activating Token Index: 220

Text #17

Max Range: 4.7442. Min Range: -4.7442

Max Act: 4.4778. Min Act: -0.1700

Data Index: 2192413 (Open Web Text)

Max Activating Token Index: 219

Text #18

Max Range: 4.7442. Min Range: -4.7442

Max Act: 4.5148. Min Act: -0.1700

Data Index: 284 (Open Web Text)

Max Activating Token Index: 537

Text #19

Max Range: 4.7442. Min Range: -4.7442

Max Act: 4.4620. Min Act: -0.1700

Data Index: 3835529 (Open Web Text)

Max Activating Token Index: 852