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

Dataset: Open Web Text

Neuron 1129 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: 3.2138. Min Range: -3.2138

Max Act: 3.2138. Min Act: -0.1700

Data Index: 7706914 (Open Web Text)

Max Activating Token Index: 216

Text #1

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.1969. Min Act: -0.1700

Data Index: 5161211 (Open Web Text)

Max Activating Token Index: 190

Text #2

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.1680. Min Act: -0.1700

Data Index: 735211 (Open Web Text)

Max Activating Token Index: 630

Text #3

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.1633. Min Act: -0.1700

Data Index: 7880724 (Open Web Text)

Max Activating Token Index: 1011

Text #4

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.1460. Min Act: -0.1700

Data Index: 8117807 (Open Web Text)

Max Activating Token Index: 674

Text #5

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.0999. Min Act: -0.1700

Data Index: 6375694 (Open Web Text)

Max Activating Token Index: 198

Text #6

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.1034. Min Act: -0.1700

Data Index: 6024127 (Open Web Text)

Max Activating Token Index: 129

Text #7

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.0976. Min Act: -0.1700

Data Index: 685889 (Open Web Text)

Max Activating Token Index: 137

Text #8

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.0938. Min Act: -0.1700

Data Index: 490377 (Open Web Text)

Max Activating Token Index: 470

Text #9

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.0291. Min Act: -0.1700

Data Index: 4457661 (Open Web Text)

Max Activating Token Index: 47

Text #10

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.0566. Min Act: -0.1700

Data Index: 2008200 (Open Web Text)

Max Activating Token Index: 768

Text #11

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.0269. Min Act: -0.1700

Data Index: 5513295 (Open Web Text)

Max Activating Token Index: 504

Text #12

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.0131. Min Act: -0.1700

Data Index: 2884316 (Open Web Text)

Max Activating Token Index: 370

Text #13

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.0093. Min Act: -0.1700

Data Index: 1327510 (Open Web Text)

Max Activating Token Index: 415

Text #14

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.0181. Min Act: -0.1700

Data Index: 1542416 (Open Web Text)

Max Activating Token Index: 784

Text #15

Max Range: 3.2138. Min Range: -3.2138

Max Act: 2.9991. Min Act: -0.1700

Data Index: 3355995 (Open Web Text)

Max Activating Token Index: 269

Text #16

Max Range: 3.2138. Min Range: -3.2138

Max Act: 2.9903. Min Act: -0.1700

Data Index: 3422818 (Open Web Text)

Max Activating Token Index: 659

Text #17

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.0033. Min Act: -0.1700

Data Index: 3359472 (Open Web Text)

Max Activating Token Index: 91

Text #18

Max Range: 3.2138. Min Range: -3.2138

Max Act: 3.0090. Min Act: -0.1700

Data Index: 3483444 (Open Web Text)

Max Activating Token Index: 559

Text #19

Max Range: 3.2138. Min Range: -3.2138

Max Act: 2.9921. Min Act: -0.1700

Data Index: 6558603 (Open Web Text)

Max Activating Token Index: 496