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

Dataset: Open Web Text

Neuron 1505 in Layer 3

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: 3.6534. Min Range: -3.6534

Max Act: 3.6534. Min Act: -0.1700

Data Index: 853215 (Open Web Text)

Max Activating Token Index: 820

Text #1

Max Range: 3.6534. Min Range: -3.6534

Max Act: 3.5995. Min Act: -0.1700

Data Index: 7459438 (Open Web Text)

Max Activating Token Index: 111

Text #2

Max Range: 3.6534. Min Range: -3.6534

Max Act: 3.5979. Min Act: -0.1700

Data Index: 6082891 (Open Web Text)

Max Activating Token Index: 299

Text #3

Max Range: 3.6534. Min Range: -3.6534

Max Act: 3.5952. Min Act: -0.1700

Data Index: 5556911 (Open Web Text)

Max Activating Token Index: 473

Text #4

Max Range: 3.6534. Min Range: -3.6534

Max Act: 3.6102. Min Act: -0.1700

Data Index: 711329 (Open Web Text)

Max Activating Token Index: 696

Text #5

Max Range: 3.6534. Min Range: -3.6534

Max Act: 3.5246. Min Act: -0.1700

Data Index: 6913185 (Open Web Text)

Max Activating Token Index: 146

Text #6

Max Range: 3.6534. Min Range: -3.6534

Max Act: 3.4680. Min Act: -0.1700

Data Index: 6544939 (Open Web Text)

Max Activating Token Index: 446

Text #7

Max Range: 3.6534. Min Range: -3.6534

Max Act: 3.4515. Min Act: -0.1700

Data Index: 6718757 (Open Web Text)

Max Activating Token Index: 146

Text #8

Max Range: 3.6534. Min Range: -3.6534

Max Act: 3.4716. Min Act: -0.1700

Data Index: 7468148 (Open Web Text)

Max Activating Token Index: 821

Text #9

Max Range: 3.6534. Min Range: -3.6534

Max Act: 3.4611. Min Act: -0.1700

Data Index: 3053087 (Open Web Text)

Max Activating Token Index: 109

Text #10

Max Range: 3.6534. Min Range: -3.6534

Max Act: 3.4858. Min Act: -0.1700

Data Index: 5399663 (Open Web Text)

Max Activating Token Index: 728

Text #11

Max Range: 3.6534. Min Range: -3.6534

Max Act: 3.4019. Min Act: -0.1700

Data Index: 8237894 (Open Web Text)

Max Activating Token Index: 592

Text #12

Max Range: 3.6534. Min Range: -3.6534

Max Act: 3.4456. Min Act: -0.1700

Data Index: 6011082 (Open Web Text)

Max Activating Token Index: 787

Text #13

Max Range: 3.6534. Min Range: -3.6534

Max Act: 3.4110. Min Act: -0.1700

Data Index: 4126610 (Open Web Text)

Max Activating Token Index: 1000

Text #14

Max Range: 3.6534. Min Range: -3.6534

Max Act: 3.4596. Min Act: -0.1700

Data Index: 2243784 (Open Web Text)

Max Activating Token Index: 690

Text #15

Max Range: 3.6534. Min Range: -3.6534

Max Act: 3.4678. Min Act: -0.1700

Data Index: 8416724 (Open Web Text)

Max Activating Token Index: 760

Text #16

Max Range: 3.6534. Min Range: -3.6534

Max Act: 3.4428. Min Act: -0.1700

Data Index: 3980218 (Open Web Text)

Max Activating Token Index: 372

Text #17

Max Range: 3.6534. Min Range: -3.6534

Max Act: 3.4236. Min Act: -0.1700

Data Index: 6361298 (Open Web Text)

Max Activating Token Index: 904

Text #18

Max Range: 3.6534. Min Range: -3.6534

Max Act: 3.3548. Min Act: -0.1700

Data Index: 71922 (Open Web Text)

Max Activating Token Index: 767

Text #19

Max Range: 3.6534. Min Range: -3.6534

Max Act: 3.3937. Min Act: -0.1700

Data Index: 5568536 (Open Web Text)

Max Activating Token Index: 438