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

Dataset: Open Web Text

Neuron 1865 in Layer 2

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: 4.5006. Min Range: -4.5006

Max Act: 4.5006. Min Act: -0.1700

Data Index: 1142948 (Open Web Text)

Max Activating Token Index: 387

Text #1

Max Range: 4.5006. Min Range: -4.5006

Max Act: 4.4155. Min Act: -0.1700

Data Index: 6477252 (Open Web Text)

Max Activating Token Index: 688

Text #2

Max Range: 4.5006. Min Range: -4.5006

Max Act: 4.3819. Min Act: -0.1700

Data Index: 6998027 (Open Web Text)

Max Activating Token Index: 710

Text #3

Max Range: 4.5006. Min Range: -4.5006

Max Act: 4.3764. Min Act: -0.1700

Data Index: 6545478 (Open Web Text)

Max Activating Token Index: 545

Text #4

Max Range: 4.5006. Min Range: -4.5006

Max Act: 4.3231. Min Act: -0.1700

Data Index: 1904259 (Open Web Text)

Max Activating Token Index: 138

Text #5

Max Range: 4.5006. Min Range: -4.5006

Max Act: 4.3338. Min Act: -0.1700

Data Index: 7297272 (Open Web Text)

Max Activating Token Index: 152

Text #6

Max Range: 4.5006. Min Range: -4.5006

Max Act: 4.3274. Min Act: -0.1700

Data Index: 8515712 (Open Web Text)

Max Activating Token Index: 368

Text #7

Max Range: 4.5006. Min Range: -4.5006

Max Act: 4.2842. Min Act: -0.1700

Data Index: 2780965 (Open Web Text)

Max Activating Token Index: 256

Text #8

Max Range: 4.5006. Min Range: -4.5006

Max Act: 4.3043. Min Act: -0.1700

Data Index: 7014831 (Open Web Text)

Max Activating Token Index: 756

Text #9

Max Range: 4.5006. Min Range: -4.5006

Max Act: 4.2759. Min Act: -0.1700

Data Index: 1772462 (Open Web Text)

Max Activating Token Index: 728

Text #10

Max Range: 4.5006. Min Range: -4.5006

Max Act: 4.2641. Min Act: -0.1700

Data Index: 526785 (Open Web Text)

Max Activating Token Index: 203

Text #11

Max Range: 4.5006. Min Range: -4.5006

Max Act: 4.2585. Min Act: -0.1700

Data Index: 1449219 (Open Web Text)

Max Activating Token Index: 932

Text #12

Max Range: 4.5006. Min Range: -4.5006

Max Act: 4.3398. Min Act: -0.1700

Data Index: 382728 (Open Web Text)

Max Activating Token Index: 381

Text #13

Max Range: 4.5006. Min Range: -4.5006

Max Act: 4.2947. Min Act: -0.1700

Data Index: 3735724 (Open Web Text)

Max Activating Token Index: 556

Text #14

Max Range: 4.5006. Min Range: -4.5006

Max Act: 4.2486. Min Act: -0.1700

Data Index: 2225047 (Open Web Text)

Max Activating Token Index: 851

Text #15

Max Range: 4.5006. Min Range: -4.5006

Max Act: 4.2545. Min Act: -0.1700

Data Index: 6579526 (Open Web Text)

Max Activating Token Index: 793

Text #16

Max Range: 4.5006. Min Range: -4.5006

Max Act: 4.2351. Min Act: -0.1700

Data Index: 290879 (Open Web Text)

Max Activating Token Index: 240

Text #17

Max Range: 4.5006. Min Range: -4.5006

Max Act: 4.2572. Min Act: -0.1700

Data Index: 1134697 (Open Web Text)

Max Activating Token Index: 617

Text #18

Max Range: 4.5006. Min Range: -4.5006

Max Act: 4.2359. Min Act: -0.1700

Data Index: 1642261 (Open Web Text)

Max Activating Token Index: 519

Text #19

Max Range: 4.5006. Min Range: -4.5006

Max Act: 4.1938. Min Act: -0.1700

Data Index: 5124598 (Open Web Text)

Max Activating Token Index: 119