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

Dataset: Open Web Text

Neuron 840 in Layer 4

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: 4.3997. Min Range: -4.3997

Max Act: 4.3997. Min Act: -0.1700

Data Index: 6667352 (Open Web Text)

Max Activating Token Index: 919

Text #1

Max Range: 4.3997. Min Range: -4.3997

Max Act: 4.1324. Min Act: -0.1700

Data Index: 4379789 (Open Web Text)

Max Activating Token Index: 774

Text #2

Max Range: 4.3997. Min Range: -4.3997

Max Act: 4.0366. Min Act: -0.1700

Data Index: 804571 (Open Web Text)

Max Activating Token Index: 535

Text #3

Max Range: 4.3997. Min Range: -4.3997

Max Act: 4.0179. Min Act: -0.1700

Data Index: 5807921 (Open Web Text)

Max Activating Token Index: 474

Text #4

Max Range: 4.3997. Min Range: -4.3997

Max Act: 4.0211. Min Act: -0.1700

Data Index: 4043542 (Open Web Text)

Max Activating Token Index: 14

Text #5

Max Range: 4.3997. Min Range: -4.3997

Max Act: 3.9575. Min Act: -0.1700

Data Index: 6823895 (Open Web Text)

Max Activating Token Index: 603

Text #6

Max Range: 4.3997. Min Range: -4.3997

Max Act: 3.9932. Min Act: -0.1700

Data Index: 7009800 (Open Web Text)

Max Activating Token Index: 831

Text #7

Max Range: 4.3997. Min Range: -4.3997

Max Act: 3.9630. Min Act: -0.1700

Data Index: 3860750 (Open Web Text)

Max Activating Token Index: 12

Text #8

Max Range: 4.3997. Min Range: -4.3997

Max Act: 3.9519. Min Act: -0.1700

Data Index: 7051453 (Open Web Text)

Max Activating Token Index: 575

Text #9

Max Range: 4.3997. Min Range: -4.3997

Max Act: 3.9421. Min Act: -0.1700

Data Index: 2742859 (Open Web Text)

Max Activating Token Index: 623

Text #10

Max Range: 4.3997. Min Range: -4.3997

Max Act: 3.8936. Min Act: -0.1700

Data Index: 5448825 (Open Web Text)

Max Activating Token Index: 740

Text #11

Max Range: 4.3997. Min Range: -4.3997

Max Act: 3.9187. Min Act: -0.1700

Data Index: 2835858 (Open Web Text)

Max Activating Token Index: 469

Text #12

Max Range: 4.3997. Min Range: -4.3997

Max Act: 3.9130. Min Act: -0.1700

Data Index: 285575 (Open Web Text)

Max Activating Token Index: 502

Text #13

Max Range: 4.3997. Min Range: -4.3997

Max Act: 3.8723. Min Act: -0.1700

Data Index: 8343566 (Open Web Text)

Max Activating Token Index: 798

Text #14

Max Range: 4.3997. Min Range: -4.3997

Max Act: 3.8974. Min Act: -0.1700

Data Index: 4478704 (Open Web Text)

Max Activating Token Index: 47

Text #15

Max Range: 4.3997. Min Range: -4.3997

Max Act: 3.8884. Min Act: -0.1700

Data Index: 5620550 (Open Web Text)

Max Activating Token Index: 203

Text #16

Max Range: 4.3997. Min Range: -4.3997

Max Act: 3.9068. Min Act: -0.1700

Data Index: 6903972 (Open Web Text)

Max Activating Token Index: 946

Text #17

Max Range: 4.3997. Min Range: -4.3997

Max Act: 3.8545. Min Act: -0.1700

Data Index: 2060604 (Open Web Text)

Max Activating Token Index: 19

Text #18

Max Range: 4.3997. Min Range: -4.3997

Max Act: 3.8603. Min Act: -0.1700

Data Index: 244501 (Open Web Text)

Max Activating Token Index: 467

Text #19

Max Range: 4.3997. Min Range: -4.3997

Max Act: 3.8748. Min Act: -0.1700

Data Index: 5805499 (Open Web Text)

Max Activating Token Index: 112