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

Dataset: Open Web Text

Neuron 2387 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: 1.6477. Min Range: -1.6477

Max Act: 1.6477. Min Act: -0.1700

Data Index: 8301281 (Open Web Text)

Max Activating Token Index: 74

Text #1

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.6282. Min Act: -0.1693

Data Index: 6636790 (Open Web Text)

Max Activating Token Index: 460

Text #2

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.6423. Min Act: -0.1700

Data Index: 2751585 (Open Web Text)

Max Activating Token Index: 434

Text #3

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.6146. Min Act: -0.1700

Data Index: 1262250 (Open Web Text)

Max Activating Token Index: 264

Text #4

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.6314. Min Act: -0.1700

Data Index: 8242893 (Open Web Text)

Max Activating Token Index: 523

Text #5

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.6233. Min Act: -0.1700

Data Index: 6527777 (Open Web Text)

Max Activating Token Index: 21

Text #6

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.6054. Min Act: -0.1700

Data Index: 617235 (Open Web Text)

Max Activating Token Index: 540

Text #7

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.6062. Min Act: -0.1699

Data Index: 4762475 (Open Web Text)

Max Activating Token Index: 825

Text #8

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.6093. Min Act: -0.1700

Data Index: 4618959 (Open Web Text)

Max Activating Token Index: 967

Text #9

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.5938. Min Act: -0.1681

Data Index: 7280690 (Open Web Text)

Max Activating Token Index: 254

Text #10

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.5695. Min Act: -0.1700

Data Index: 2073249 (Open Web Text)

Max Activating Token Index: 608

Text #11

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.5614. Min Act: -0.1691

Data Index: 146529 (Open Web Text)

Max Activating Token Index: 229

Text #12

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.5649. Min Act: -0.1700

Data Index: 1407644 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.5591. Min Act: -0.1700

Data Index: 8452249 (Open Web Text)

Max Activating Token Index: 615

Text #14

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.5601. Min Act: -0.1700

Data Index: 1805551 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.5355. Min Act: -0.1699

Data Index: 5495 (Open Web Text)

Max Activating Token Index: 946

Text #16

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.5497. Min Act: -0.1700

Data Index: 5077 (Open Web Text)

Max Activating Token Index: 123

Text #17

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.5444. Min Act: -0.1683

Data Index: 1517678 (Open Web Text)

Max Activating Token Index: 829

Text #18

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.5420. Min Act: -0.1700

Data Index: 6208191 (Open Web Text)

Max Activating Token Index: 81

Text #19

Max Range: 1.6477. Min Range: -1.6477

Max Act: 1.5439. Min Act: -0.1698

Data Index: 3854665 (Open Web Text)

Max Activating Token Index: 22