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

Dataset: Open Web Text

Neuron 1811 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: 3.9614. Min Range: -3.9614

Max Act: 3.9025. Min Act: -0.1700

Data Index: 990306 (Open Web Text)

Max Activating Token Index: 586

Text #1

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.9614. Min Act: -0.1700

Data Index: 3638260 (Open Web Text)

Max Activating Token Index: 831

Text #2

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.7732. Min Act: -0.1700

Data Index: 7062376 (Open Web Text)

Max Activating Token Index: 808

Text #3

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.9572. Min Act: -0.1700

Data Index: 1485585 (Open Web Text)

Max Activating Token Index: 184

Text #4

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.8342. Min Act: -0.1700

Data Index: 3983839 (Open Web Text)

Max Activating Token Index: 97

Text #5

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.8166. Min Act: -0.1700

Data Index: 7280710 (Open Web Text)

Max Activating Token Index: 180

Text #6

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.7902. Min Act: -0.1700

Data Index: 871795 (Open Web Text)

Max Activating Token Index: 685

Text #7

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.8035. Min Act: -0.1700

Data Index: 7400063 (Open Web Text)

Max Activating Token Index: 770

Text #8

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.6642. Min Act: -0.1700

Data Index: 6553500 (Open Web Text)

Max Activating Token Index: 800

Text #9

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.6784. Min Act: -0.1700

Data Index: 268268 (Open Web Text)

Max Activating Token Index: 190

Text #10

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.6860. Min Act: -0.1700

Data Index: 1652589 (Open Web Text)

Max Activating Token Index: 679

Text #11

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.6331. Min Act: -0.1700

Data Index: 157834 (Open Web Text)

Max Activating Token Index: 870

Text #12

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.7032. Min Act: -0.1700

Data Index: 7034112 (Open Web Text)

Max Activating Token Index: 579

Text #13

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.7385. Min Act: -0.1700

Data Index: 3464770 (Open Web Text)

Max Activating Token Index: 363

Text #14

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.6957. Min Act: -0.1700

Data Index: 5654933 (Open Web Text)

Max Activating Token Index: 476

Text #15

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.6432. Min Act: -0.1700

Data Index: 4156243 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.6648. Min Act: -0.1700

Data Index: 3489425 (Open Web Text)

Max Activating Token Index: 34

Text #17

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.6736. Min Act: -0.1700

Data Index: 3747119 (Open Web Text)

Max Activating Token Index: 97

Text #18

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.6800. Min Act: -0.1700

Data Index: 3489426 (Open Web Text)

Max Activating Token Index: 334

Text #19

Max Range: 3.9614. Min Range: -3.9614

Max Act: 3.6551. Min Act: -0.1700

Data Index: 7166404 (Open Web Text)

Max Activating Token Index: 504