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

Dataset: Open Web Text

Neuron 2489 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: 4.9601. Min Range: -4.9601

Max Act: 4.9601. Min Act: -0.1700

Data Index: 5103900 (Open Web Text)

Max Activating Token Index: 785

Text #1

Max Range: 4.9601. Min Range: -4.9601

Max Act: 4.9259. Min Act: -0.1700

Data Index: 8477808 (Open Web Text)

Max Activating Token Index: 791

Text #2

Max Range: 4.9601. Min Range: -4.9601

Max Act: 4.8948. Min Act: -0.1700

Data Index: 6171593 (Open Web Text)

Max Activating Token Index: 792

Text #3

Max Range: 4.9601. Min Range: -4.9601

Max Act: 4.8307. Min Act: -0.1700

Data Index: 8477793 (Open Web Text)

Max Activating Token Index: 903

Text #4

Max Range: 4.9601. Min Range: -4.9601

Max Act: 4.7833. Min Act: -0.1700

Data Index: 5255650 (Open Web Text)

Max Activating Token Index: 878

Text #5

Max Range: 4.9601. Min Range: -4.9601

Max Act: 4.7997. Min Act: -0.1700

Data Index: 6035299 (Open Web Text)

Max Activating Token Index: 800

Text #6

Max Range: 4.9601. Min Range: -4.9601

Max Act: 4.7995. Min Act: -0.1700

Data Index: 4983238 (Open Web Text)

Max Activating Token Index: 553

Text #7

Max Range: 4.9601. Min Range: -4.9601

Max Act: 4.7752. Min Act: -0.1700

Data Index: 7971444 (Open Web Text)

Max Activating Token Index: 768

Text #8

Max Range: 4.9601. Min Range: -4.9601

Max Act: 4.7903. Min Act: -0.1700

Data Index: 7264208 (Open Web Text)

Max Activating Token Index: 470

Text #9

Max Range: 4.9601. Min Range: -4.9601

Max Act: 4.8028. Min Act: -0.1700

Data Index: 4019177 (Open Web Text)

Max Activating Token Index: 762

Text #10

Max Range: 4.9601. Min Range: -4.9601

Max Act: 4.7688. Min Act: -0.1700

Data Index: 5660610 (Open Web Text)

Max Activating Token Index: 65

Text #11

Max Range: 4.9601. Min Range: -4.9601

Max Act: 4.7697. Min Act: -0.1700

Data Index: 6717727 (Open Web Text)

Max Activating Token Index: 357

Text #12

Max Range: 4.9601. Min Range: -4.9601

Max Act: 4.7545. Min Act: -0.1700

Data Index: 5255643 (Open Web Text)

Max Activating Token Index: 374

Text #13

Max Range: 4.9601. Min Range: -4.9601

Max Act: 4.7783. Min Act: -0.1700

Data Index: 5103897 (Open Web Text)

Max Activating Token Index: 772

Text #14

Max Range: 4.9601. Min Range: -4.9601

Max Act: 4.7719. Min Act: -0.1700

Data Index: 4983239 (Open Web Text)

Max Activating Token Index: 454

Text #15

Max Range: 4.9601. Min Range: -4.9601

Max Act: 4.7556. Min Act: -0.1700

Data Index: 6018345 (Open Web Text)

Max Activating Token Index: 163

Text #16

Max Range: 4.9601. Min Range: -4.9601

Max Act: 4.7800. Min Act: -0.1700

Data Index: 3683840 (Open Web Text)

Max Activating Token Index: 348

Text #17

Max Range: 4.9601. Min Range: -4.9601

Max Act: 4.7589. Min Act: -0.1700

Data Index: 6018343 (Open Web Text)

Max Activating Token Index: 317

Text #18

Max Range: 4.9601. Min Range: -4.9601

Max Act: 4.7517. Min Act: -0.1700

Data Index: 6018332 (Open Web Text)

Max Activating Token Index: 664

Text #19

Max Range: 4.9601. Min Range: -4.9601

Max Act: 4.7383. Min Act: -0.1700

Data Index: 6110616 (Open Web Text)

Max Activating Token Index: 380