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

Dataset: Open Web Text

Neuron 334 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: 5.4535. Min Range: -5.4535

Max Act: 5.4535. Min Act: -0.1700

Data Index: 4979175 (Open Web Text)

Max Activating Token Index: 284

Text #1

Max Range: 5.4535. Min Range: -5.4535

Max Act: 5.1999. Min Act: -0.1700

Data Index: 2023364 (Open Web Text)

Max Activating Token Index: 373

Text #2

Max Range: 5.4535. Min Range: -5.4535

Max Act: 5.1444. Min Act: -0.1700

Data Index: 4229442 (Open Web Text)

Max Activating Token Index: 702

Text #3

Max Range: 5.4535. Min Range: -5.4535

Max Act: 5.0806. Min Act: -0.1700

Data Index: 2160319 (Open Web Text)

Max Activating Token Index: 869

Text #4

Max Range: 5.4535. Min Range: -5.4535

Max Act: 5.0120. Min Act: -0.1700

Data Index: 928889 (Open Web Text)

Max Activating Token Index: 842

Text #5

Max Range: 5.4535. Min Range: -5.4535

Max Act: 5.0556. Min Act: -0.1700

Data Index: 266791 (Open Web Text)

Max Activating Token Index: 605

Text #6

Max Range: 5.4535. Min Range: -5.4535

Max Act: 4.9656. Min Act: -0.1700

Data Index: 1881283 (Open Web Text)

Max Activating Token Index: 153

Text #7

Max Range: 5.4535. Min Range: -5.4535

Max Act: 4.9456. Min Act: -0.1700

Data Index: 3413036 (Open Web Text)

Max Activating Token Index: 326

Text #8

Max Range: 5.4535. Min Range: -5.4535

Max Act: 4.9451. Min Act: -0.1700

Data Index: 2461819 (Open Web Text)

Max Activating Token Index: 547

Text #9

Max Range: 5.4535. Min Range: -5.4535

Max Act: 4.9223. Min Act: -0.1700

Data Index: 7964032 (Open Web Text)

Max Activating Token Index: 805

Text #10

Max Range: 5.4535. Min Range: -5.4535

Max Act: 4.9102. Min Act: -0.1700

Data Index: 3965530 (Open Web Text)

Max Activating Token Index: 177

Text #11

Max Range: 5.4535. Min Range: -5.4535

Max Act: 4.8875. Min Act: -0.1700

Data Index: 497391 (Open Web Text)

Max Activating Token Index: 645

Text #12

Max Range: 5.4535. Min Range: -5.4535

Max Act: 4.8853. Min Act: -0.1700

Data Index: 8330789 (Open Web Text)

Max Activating Token Index: 484

Text #13

Max Range: 5.4535. Min Range: -5.4535

Max Act: 4.8940. Min Act: -0.1700

Data Index: 2809929 (Open Web Text)

Max Activating Token Index: 403

Text #14

Max Range: 5.4535. Min Range: -5.4535

Max Act: 4.9094. Min Act: -0.1700

Data Index: 4078646 (Open Web Text)

Max Activating Token Index: 852

Text #15

Max Range: 5.4535. Min Range: -5.4535

Max Act: 4.8800. Min Act: -0.1700

Data Index: 2718936 (Open Web Text)

Max Activating Token Index: 863

Text #16

Max Range: 5.4535. Min Range: -5.4535

Max Act: 4.7944. Min Act: -0.1700

Data Index: 654346 (Open Web Text)

Max Activating Token Index: 832

Text #17

Max Range: 5.4535. Min Range: -5.4535

Max Act: 4.8333. Min Act: -0.1700

Data Index: 4731995 (Open Web Text)

Max Activating Token Index: 531

Text #18

Max Range: 5.4535. Min Range: -5.4535

Max Act: 4.8224. Min Act: -0.1700

Data Index: 211997 (Open Web Text)

Max Activating Token Index: 1020

Text #19

Max Range: 5.4535. Min Range: -5.4535

Max Act: 4.8272. Min Act: -0.1700

Data Index: 7164695 (Open Web Text)

Max Activating Token Index: 232