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

Dataset: Open Web Text

Neuron 1050 in Layer 4

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: 2.0202. Min Range: -2.0202

Max Act: 2.0202. Min Act: -0.1700

Data Index: 347172 (Open Web Text)

Max Activating Token Index: 730

Text #1

Max Range: 2.0202. Min Range: -2.0202

Max Act: 2.0043. Min Act: -0.1700

Data Index: 5426587 (Open Web Text)

Max Activating Token Index: 925

Text #2

Max Range: 2.0202. Min Range: -2.0202

Max Act: 1.9671. Min Act: -0.1700

Data Index: 1384880 (Open Web Text)

Max Activating Token Index: 282

Text #3

Max Range: 2.0202. Min Range: -2.0202

Max Act: 1.9908. Min Act: -0.1700

Data Index: 8467387 (Open Web Text)

Max Activating Token Index: 119

Text #4

Max Range: 2.0202. Min Range: -2.0202

Max Act: 1.9518. Min Act: -0.1700

Data Index: 3970551 (Open Web Text)

Max Activating Token Index: 142

Text #5

Max Range: 2.0202. Min Range: -2.0202

Max Act: 1.9071. Min Act: -0.1700

Data Index: 5173550 (Open Web Text)

Max Activating Token Index: 537

Text #6

Max Range: 2.0202. Min Range: -2.0202

Max Act: 1.9128. Min Act: -0.1700

Data Index: 4353177 (Open Web Text)

Max Activating Token Index: 745

Text #7

Max Range: 2.0202. Min Range: -2.0202

Max Act: 1.8950. Min Act: -0.1700

Data Index: 4188415 (Open Web Text)

Max Activating Token Index: 240

Text #8

Max Range: 2.0202. Min Range: -2.0202

Max Act: 1.9069. Min Act: -0.1700

Data Index: 1675439 (Open Web Text)

Max Activating Token Index: 660

Text #9

Max Range: 2.0202. Min Range: -2.0202

Max Act: 1.8851. Min Act: -0.1700

Data Index: 4438372 (Open Web Text)

Max Activating Token Index: 429

Text #10

Max Range: 2.0202. Min Range: -2.0202

Max Act: 1.8568. Min Act: -0.1700

Data Index: 5980335 (Open Web Text)

Max Activating Token Index: 992

Text #11

Max Range: 2.0202. Min Range: -2.0202

Max Act: 1.8923. Min Act: -0.1700

Data Index: 789718 (Open Web Text)

Max Activating Token Index: 911

Text #12

Max Range: 2.0202. Min Range: -2.0202

Max Act: 1.8719. Min Act: -0.1700

Data Index: 1057490 (Open Web Text)

Max Activating Token Index: 342

Text #13

Max Range: 2.0202. Min Range: -2.0202

Max Act: 1.8695. Min Act: -0.1700

Data Index: 5964158 (Open Web Text)

Max Activating Token Index: 519

Text #14

Max Range: 2.0202. Min Range: -2.0202

Max Act: 1.8480. Min Act: -0.1700

Data Index: 228307 (Open Web Text)

Max Activating Token Index: 55

Text #15

Max Range: 2.0202. Min Range: -2.0202

Max Act: 1.8215. Min Act: -0.1700

Data Index: 7341026 (Open Web Text)

Max Activating Token Index: 598

Text #16

Max Range: 2.0202. Min Range: -2.0202

Max Act: 1.8590. Min Act: -0.1700

Data Index: 1492948 (Open Web Text)

Max Activating Token Index: 986

Text #17

Max Range: 2.0202. Min Range: -2.0202

Max Act: 1.8284. Min Act: -0.1700

Data Index: 3315062 (Open Web Text)

Max Activating Token Index: 843

Text #18

Max Range: 2.0202. Min Range: -2.0202

Max Act: 1.8415. Min Act: -0.1700

Data Index: 7327437 (Open Web Text)

Max Activating Token Index: 886

Text #19

Max Range: 2.0202. Min Range: -2.0202

Max Act: 1.8267. Min Act: -0.1700

Data Index: 3067613 (Open Web Text)

Max Activating Token Index: 670