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

Dataset: Open Web Text

Neuron 1075 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: 1.6054. Min Range: -1.6054

Max Act: 1.6054. Min Act: -0.1664

Data Index: 4517484 (Open Web Text)

Max Activating Token Index: 128

Text #1

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.5862. Min Act: -0.1681

Data Index: 1668725 (Open Web Text)

Max Activating Token Index: 647

Text #2

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.5501. Min Act: -0.1700

Data Index: 4517483 (Open Web Text)

Max Activating Token Index: 807

Text #3

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.5369. Min Act: -0.1681

Data Index: 5516562 (Open Web Text)

Max Activating Token Index: 589

Text #4

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.5352. Min Act: -0.1694

Data Index: 2540397 (Open Web Text)

Max Activating Token Index: 573

Text #5

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.5174. Min Act: -0.1700

Data Index: 7023181 (Open Web Text)

Max Activating Token Index: 125

Text #6

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.5066. Min Act: -0.1700

Data Index: 7215315 (Open Web Text)

Max Activating Token Index: 21

Text #7

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.5150. Min Act: -0.1700

Data Index: 3690562 (Open Web Text)

Max Activating Token Index: 33

Text #8

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.5097. Min Act: -0.1700

Data Index: 2587872 (Open Web Text)

Max Activating Token Index: 84

Text #9

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.5070. Min Act: -0.1662

Data Index: 5516561 (Open Web Text)

Max Activating Token Index: 541

Text #10

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.5073. Min Act: -0.1686

Data Index: 3807464 (Open Web Text)

Max Activating Token Index: 264

Text #11

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.5115. Min Act: -0.1696

Data Index: 5144033 (Open Web Text)

Max Activating Token Index: 595

Text #12

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.4938. Min Act: -0.1700

Data Index: 3604904 (Open Web Text)

Max Activating Token Index: 237

Text #13

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.4985. Min Act: -0.1674

Data Index: 3914496 (Open Web Text)

Max Activating Token Index: 446

Text #14

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.4899. Min Act: -0.1699

Data Index: 4148624 (Open Web Text)

Max Activating Token Index: 24

Text #15

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.4943. Min Act: -0.1694

Data Index: 2861844 (Open Web Text)

Max Activating Token Index: 555

Text #16

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.4799. Min Act: -0.1694

Data Index: 8127303 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.4753. Min Act: -0.1699

Data Index: 7868744 (Open Web Text)

Max Activating Token Index: 42

Text #18

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.4735. Min Act: -0.1687

Data Index: 1308441 (Open Web Text)

Max Activating Token Index: 514

Text #19

Max Range: 1.6054. Min Range: -1.6054

Max Act: 1.4717. Min Act: -0.1699

Data Index: 2157511 (Open Web Text)

Max Activating Token Index: 38