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

Dataset: Open Web Text

Neuron 587 in Layer 1

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: 1.8145. Min Range: -1.8145

Max Act: 1.8145. Min Act: -0.1700

Data Index: 2761629 (Open Web Text)

Max Activating Token Index: 370

Text #1

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.8142. Min Act: -0.1700

Data Index: 574064 (Open Web Text)

Max Activating Token Index: 51

Text #2

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.8019. Min Act: -0.1699

Data Index: 8530747 (Open Web Text)

Max Activating Token Index: 69

Text #3

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.7809. Min Act: -0.1700

Data Index: 5971443 (Open Web Text)

Max Activating Token Index: 15

Text #4

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.7713. Min Act: -0.1700

Data Index: 2527297 (Open Web Text)

Max Activating Token Index: 434

Text #5

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.7695. Min Act: -0.1700

Data Index: 4291645 (Open Web Text)

Max Activating Token Index: 278

Text #6

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.7683. Min Act: -0.1700

Data Index: 2903796 (Open Web Text)

Max Activating Token Index: 339

Text #7

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.7752. Min Act: -0.1700

Data Index: 4708060 (Open Web Text)

Max Activating Token Index: 931

Text #8

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.7698. Min Act: -0.1698

Data Index: 7832621 (Open Web Text)

Max Activating Token Index: 263

Text #9

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.7516. Min Act: -0.1700

Data Index: 1542556 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.7626. Min Act: -0.1700

Data Index: 3493179 (Open Web Text)

Max Activating Token Index: 650

Text #11

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.7500. Min Act: -0.1699

Data Index: 7221078 (Open Web Text)

Max Activating Token Index: 401

Text #12

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.7504. Min Act: -0.1699

Data Index: 2356077 (Open Web Text)

Max Activating Token Index: 126

Text #13

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.7530. Min Act: -0.1700

Data Index: 7841252 (Open Web Text)

Max Activating Token Index: 839

Text #14

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.7481. Min Act: -0.1700

Data Index: 3102778 (Open Web Text)

Max Activating Token Index: 592

Text #15

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.7424. Min Act: -0.1700

Data Index: 6393549 (Open Web Text)

Max Activating Token Index: 730

Text #16

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.7344. Min Act: -0.1700

Data Index: 2346610 (Open Web Text)

Max Activating Token Index: 691

Text #17

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.7496. Min Act: -0.1700

Data Index: 2138307 (Open Web Text)

Max Activating Token Index: 1022

Text #18

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.7321. Min Act: -0.1700

Data Index: 1761207 (Open Web Text)

Max Activating Token Index: 146

Text #19

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.7389. Min Act: -0.1700

Data Index: 3194873 (Open Web Text)

Max Activating Token Index: 401