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

Dataset: Open Web Text

Neuron 1059 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: 1.6299. Min Range: -1.6299

Max Act: 1.6299. Min Act: -0.1700

Data Index: 533614 (Open Web Text)

Max Activating Token Index: 69

Text #1

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.6287. Min Act: -0.1700

Data Index: 2639880 (Open Web Text)

Max Activating Token Index: 462

Text #2

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.6230. Min Act: -0.1700

Data Index: 1061371 (Open Web Text)

Max Activating Token Index: 485

Text #3

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.6276. Min Act: -0.1700

Data Index: 696387 (Open Web Text)

Max Activating Token Index: 57

Text #4

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.6258. Min Act: -0.1700

Data Index: 8472889 (Open Web Text)

Max Activating Token Index: 214

Text #5

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.6039. Min Act: -0.1700

Data Index: 8813367 (Open Web Text)

Max Activating Token Index: 426

Text #6

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.5987. Min Act: -0.1700

Data Index: 5729482 (Open Web Text)

Max Activating Token Index: 699

Text #7

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.5933. Min Act: -0.1700

Data Index: 5561687 (Open Web Text)

Max Activating Token Index: 299

Text #8

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.5876. Min Act: -0.1700

Data Index: 4323854 (Open Web Text)

Max Activating Token Index: 51

Text #9

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.5903. Min Act: -0.1700

Data Index: 8322702 (Open Web Text)

Max Activating Token Index: 94

Text #10

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.5947. Min Act: -0.1700

Data Index: 2018077 (Open Web Text)

Max Activating Token Index: 104

Text #11

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.5859. Min Act: -0.1700

Data Index: 5455895 (Open Web Text)

Max Activating Token Index: 1022

Text #12

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.5892. Min Act: -0.1700

Data Index: 1646484 (Open Web Text)

Max Activating Token Index: 1016

Text #13

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.5945. Min Act: -0.1700

Data Index: 6496921 (Open Web Text)

Max Activating Token Index: 109

Text #14

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.5813. Min Act: -0.1700

Data Index: 628607 (Open Web Text)

Max Activating Token Index: 543

Text #15

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.5863. Min Act: -0.1700

Data Index: 8723272 (Open Web Text)

Max Activating Token Index: 779

Text #16

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.5900. Min Act: -0.1700

Data Index: 3522693 (Open Web Text)

Max Activating Token Index: 64

Text #17

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.5828. Min Act: -0.1700

Data Index: 6028079 (Open Web Text)

Max Activating Token Index: 814

Text #18

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.5882. Min Act: -0.1700

Data Index: 1383290 (Open Web Text)

Max Activating Token Index: 127

Text #19

Max Range: 1.6299. Min Range: -1.6299

Max Act: 1.5664. Min Act: -0.1700

Data Index: 2307707 (Open Web Text)

Max Activating Token Index: 370