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

Dataset: Open Web Text

Neuron 1798 in Layer 6

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: 4.0294. Min Range: -4.0294

Max Act: 4.0294. Min Act: -0.1700

Data Index: 3709473 (Open Web Text)

Max Activating Token Index: 806

Text #1

Max Range: 4.0294. Min Range: -4.0294

Max Act: 3.9613. Min Act: -0.1700

Data Index: 2302385 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.0294. Min Range: -4.0294

Max Act: 3.9360. Min Act: -0.1700

Data Index: 5834386 (Open Web Text)

Max Activating Token Index: 68

Text #3

Max Range: 4.0294. Min Range: -4.0294

Max Act: 3.9101. Min Act: -0.1700

Data Index: 1217528 (Open Web Text)

Max Activating Token Index: 262

Text #4

Max Range: 4.0294. Min Range: -4.0294

Max Act: 3.9001. Min Act: -0.1700

Data Index: 1092771 (Open Web Text)

Max Activating Token Index: 198

Text #5

Max Range: 4.0294. Min Range: -4.0294

Max Act: 3.8207. Min Act: -0.1700

Data Index: 3898497 (Open Web Text)

Max Activating Token Index: 455

Text #6

Max Range: 4.0294. Min Range: -4.0294

Max Act: 3.8264. Min Act: -0.1700

Data Index: 4868699 (Open Web Text)

Max Activating Token Index: 837

Text #7

Max Range: 4.0294. Min Range: -4.0294

Max Act: 3.7889. Min Act: -0.1700

Data Index: 3652576 (Open Web Text)

Max Activating Token Index: 904

Text #8

Max Range: 4.0294. Min Range: -4.0294

Max Act: 3.8094. Min Act: -0.1700

Data Index: 165089 (Open Web Text)

Max Activating Token Index: 640

Text #9

Max Range: 4.0294. Min Range: -4.0294

Max Act: 3.7835. Min Act: -0.1700

Data Index: 1848452 (Open Web Text)

Max Activating Token Index: 84

Text #10

Max Range: 4.0294. Min Range: -4.0294

Max Act: 3.7890. Min Act: -0.1700

Data Index: 2551166 (Open Web Text)

Max Activating Token Index: 207

Text #11

Max Range: 4.0294. Min Range: -4.0294

Max Act: 3.7729. Min Act: -0.1700

Data Index: 6323502 (Open Web Text)

Max Activating Token Index: 80

Text #12

Max Range: 4.0294. Min Range: -4.0294

Max Act: 3.7640. Min Act: -0.1700

Data Index: 3542569 (Open Web Text)

Max Activating Token Index: 881

Text #13

Max Range: 4.0294. Min Range: -4.0294

Max Act: 3.7928. Min Act: -0.1700

Data Index: 7415633 (Open Web Text)

Max Activating Token Index: 459

Text #14

Max Range: 4.0294. Min Range: -4.0294

Max Act: 3.7718. Min Act: -0.1700

Data Index: 671830 (Open Web Text)

Max Activating Token Index: 861

Text #15

Max Range: 4.0294. Min Range: -4.0294

Max Act: 3.7616. Min Act: -0.1700

Data Index: 176159 (Open Web Text)

Max Activating Token Index: 803

Text #16

Max Range: 4.0294. Min Range: -4.0294

Max Act: 3.7221. Min Act: -0.1700

Data Index: 3189120 (Open Web Text)

Max Activating Token Index: 572

Text #17

Max Range: 4.0294. Min Range: -4.0294

Max Act: 3.7102. Min Act: -0.1700

Data Index: 4846763 (Open Web Text)

Max Activating Token Index: 678

Text #18

Max Range: 4.0294. Min Range: -4.0294

Max Act: 3.7289. Min Act: -0.1700

Data Index: 1864069 (Open Web Text)

Max Activating Token Index: 214

Text #19

Max Range: 4.0294. Min Range: -4.0294

Max Act: 3.7295. Min Act: -0.1700

Data Index: 2194424 (Open Web Text)

Max Activating Token Index: 193