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

Dataset: Open Web Text

Neuron 1678 in Layer 5

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: 7.1991. Min Range: -7.1991

Max Act: 7.1991. Min Act: -0.1700

Data Index: 5078460 (Open Web Text)

Max Activating Token Index: 368

Text #1

Max Range: 7.1991. Min Range: -7.1991

Max Act: 7.0037. Min Act: -0.1700

Data Index: 917221 (Open Web Text)

Max Activating Token Index: 540

Text #2

Max Range: 7.1991. Min Range: -7.1991

Max Act: 6.8941. Min Act: -0.1700

Data Index: 7338106 (Open Web Text)

Max Activating Token Index: 347

Text #3

Max Range: 7.1991. Min Range: -7.1991

Max Act: 6.8377. Min Act: -0.1700

Data Index: 496288 (Open Web Text)

Max Activating Token Index: 853

Text #4

Max Range: 7.1991. Min Range: -7.1991

Max Act: 6.7198. Min Act: -0.1700

Data Index: 7058331 (Open Web Text)

Max Activating Token Index: 569

Text #5

Max Range: 7.1991. Min Range: -7.1991

Max Act: 6.6763. Min Act: -0.1700

Data Index: 6248508 (Open Web Text)

Max Activating Token Index: 698

Text #6

Max Range: 7.1991. Min Range: -7.1991

Max Act: 6.6899. Min Act: -0.1700

Data Index: 7528169 (Open Web Text)

Max Activating Token Index: 935

Text #7

Max Range: 7.1991. Min Range: -7.1991

Max Act: 6.6529. Min Act: -0.1700

Data Index: 6328049 (Open Web Text)

Max Activating Token Index: 536

Text #8

Max Range: 7.1991. Min Range: -7.1991

Max Act: 6.6626. Min Act: -0.1700

Data Index: 4784803 (Open Web Text)

Max Activating Token Index: 511

Text #9

Max Range: 7.1991. Min Range: -7.1991

Max Act: 6.6331. Min Act: -0.1700

Data Index: 3598823 (Open Web Text)

Max Activating Token Index: 828

Text #10

Max Range: 7.1991. Min Range: -7.1991

Max Act: 6.5863. Min Act: -0.1700

Data Index: 8047494 (Open Web Text)

Max Activating Token Index: 776

Text #11

Max Range: 7.1991. Min Range: -7.1991

Max Act: 6.5899. Min Act: -0.1700

Data Index: 1426026 (Open Web Text)

Max Activating Token Index: 330

Text #12

Max Range: 7.1991. Min Range: -7.1991

Max Act: 6.5433. Min Act: -0.1700

Data Index: 4565020 (Open Web Text)

Max Activating Token Index: 740

Text #13

Max Range: 7.1991. Min Range: -7.1991

Max Act: 6.5990. Min Act: -0.1700

Data Index: 4014703 (Open Web Text)

Max Activating Token Index: 364

Text #14

Max Range: 7.1991. Min Range: -7.1991

Max Act: 6.5660. Min Act: -0.1700

Data Index: 7477501 (Open Web Text)

Max Activating Token Index: 607

Text #15

Max Range: 7.1991. Min Range: -7.1991

Max Act: 6.5007. Min Act: -0.1700

Data Index: 5889615 (Open Web Text)

Max Activating Token Index: 99

Text #16

Max Range: 7.1991. Min Range: -7.1991

Max Act: 6.4364. Min Act: -0.1700

Data Index: 5402349 (Open Web Text)

Max Activating Token Index: 383

Text #17

Max Range: 7.1991. Min Range: -7.1991

Max Act: 6.4733. Min Act: -0.1700

Data Index: 6960336 (Open Web Text)

Max Activating Token Index: 997

Text #18

Max Range: 7.1991. Min Range: -7.1991

Max Act: 6.4505. Min Act: -0.1700

Data Index: 4638601 (Open Web Text)

Max Activating Token Index: 488

Text #19

Max Range: 7.1991. Min Range: -7.1991

Max Act: 6.4986. Min Act: -0.1700

Data Index: 4873995 (Open Web Text)

Max Activating Token Index: 997