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

Dataset: Open Web Text

Neuron 362 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: 4.6219. Min Range: -4.6219

Max Act: 4.6219. Min Act: -0.1700

Data Index: 2617787 (Open Web Text)

Max Activating Token Index: 526

Text #1

Max Range: 4.6219. Min Range: -4.6219

Max Act: 4.5825. Min Act: -0.1700

Data Index: 6560700 (Open Web Text)

Max Activating Token Index: 692

Text #2

Max Range: 4.6219. Min Range: -4.6219

Max Act: 4.5095. Min Act: -0.1700

Data Index: 3324486 (Open Web Text)

Max Activating Token Index: 171

Text #3

Max Range: 4.6219. Min Range: -4.6219

Max Act: 4.4879. Min Act: -0.1700

Data Index: 6672594 (Open Web Text)

Max Activating Token Index: 82

Text #4

Max Range: 4.6219. Min Range: -4.6219

Max Act: 4.4189. Min Act: -0.1700

Data Index: 3401826 (Open Web Text)

Max Activating Token Index: 613

Text #5

Max Range: 4.6219. Min Range: -4.6219

Max Act: 4.4275. Min Act: -0.1700

Data Index: 695457 (Open Web Text)

Max Activating Token Index: 898

Text #6

Max Range: 4.6219. Min Range: -4.6219

Max Act: 4.4158. Min Act: -0.1700

Data Index: 5034140 (Open Web Text)

Max Activating Token Index: 387

Text #7

Max Range: 4.6219. Min Range: -4.6219

Max Act: 4.4360. Min Act: -0.1700

Data Index: 6686852 (Open Web Text)

Max Activating Token Index: 797

Text #8

Max Range: 4.6219. Min Range: -4.6219

Max Act: 4.3887. Min Act: -0.1700

Data Index: 3034767 (Open Web Text)

Max Activating Token Index: 556

Text #9

Max Range: 4.6219. Min Range: -4.6219

Max Act: 4.4233. Min Act: -0.1700

Data Index: 6678384 (Open Web Text)

Max Activating Token Index: 627

Text #10

Max Range: 4.6219. Min Range: -4.6219

Max Act: 4.4272. Min Act: -0.1700

Data Index: 7181029 (Open Web Text)

Max Activating Token Index: 661

Text #11

Max Range: 4.6219. Min Range: -4.6219

Max Act: 4.3977. Min Act: -0.1700

Data Index: 4450283 (Open Web Text)

Max Activating Token Index: 369

Text #12

Max Range: 4.6219. Min Range: -4.6219

Max Act: 4.3980. Min Act: -0.1700

Data Index: 6860048 (Open Web Text)

Max Activating Token Index: 599

Text #13

Max Range: 4.6219. Min Range: -4.6219

Max Act: 4.3826. Min Act: -0.1700

Data Index: 3045164 (Open Web Text)

Max Activating Token Index: 261

Text #14

Max Range: 4.6219. Min Range: -4.6219

Max Act: 4.3555. Min Act: -0.1700

Data Index: 4763928 (Open Web Text)

Max Activating Token Index: 839

Text #15

Max Range: 4.6219. Min Range: -4.6219

Max Act: 4.3925. Min Act: -0.1700

Data Index: 7210063 (Open Web Text)

Max Activating Token Index: 977

Text #16

Max Range: 4.6219. Min Range: -4.6219

Max Act: 4.3790. Min Act: -0.1700

Data Index: 8483593 (Open Web Text)

Max Activating Token Index: 574

Text #17

Max Range: 4.6219. Min Range: -4.6219

Max Act: 4.3755. Min Act: -0.1700

Data Index: 5110411 (Open Web Text)

Max Activating Token Index: 519

Text #18

Max Range: 4.6219. Min Range: -4.6219

Max Act: 4.3772. Min Act: -0.1700

Data Index: 5519854 (Open Web Text)

Max Activating Token Index: 695

Text #19

Max Range: 4.6219. Min Range: -4.6219

Max Act: 4.3522. Min Act: -0.1700

Data Index: 676293 (Open Web Text)

Max Activating Token Index: 199