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

Dataset: Open Web Text

Neuron 554 in Layer 1

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: 1.9848. Min Range: -1.9848

Max Act: 1.9848. Min Act: -0.1700

Data Index: 7642768 (Open Web Text)

Max Activating Token Index: 359

Text #1

Max Range: 1.9848. Min Range: -1.9848

Max Act: 1.9404. Min Act: -0.1700

Data Index: 4418106 (Open Web Text)

Max Activating Token Index: 999

Text #2

Max Range: 1.9848. Min Range: -1.9848

Max Act: 1.8994. Min Act: -0.1700

Data Index: 4073346 (Open Web Text)

Max Activating Token Index: 80

Text #3

Max Range: 1.9848. Min Range: -1.9848

Max Act: 1.8918. Min Act: -0.1700

Data Index: 5726859 (Open Web Text)

Max Activating Token Index: 728

Text #4

Max Range: 1.9848. Min Range: -1.9848

Max Act: 1.8833. Min Act: -0.1700

Data Index: 2188587 (Open Web Text)

Max Activating Token Index: 382

Text #5

Max Range: 1.9848. Min Range: -1.9848

Max Act: 1.8753. Min Act: -0.1700

Data Index: 7791908 (Open Web Text)

Max Activating Token Index: 334

Text #6

Max Range: 1.9848. Min Range: -1.9848

Max Act: 1.8570. Min Act: -0.1700

Data Index: 4370420 (Open Web Text)

Max Activating Token Index: 561

Text #7

Max Range: 1.9848. Min Range: -1.9848

Max Act: 1.8567. Min Act: -0.1699

Data Index: 431643 (Open Web Text)

Max Activating Token Index: 621

Text #8

Max Range: 1.9848. Min Range: -1.9848

Max Act: 1.8597. Min Act: -0.1700

Data Index: 5656248 (Open Web Text)

Max Activating Token Index: 494

Text #9

Max Range: 1.9848. Min Range: -1.9848

Max Act: 1.8624. Min Act: -0.1700

Data Index: 8673149 (Open Web Text)

Max Activating Token Index: 216

Text #10

Max Range: 1.9848. Min Range: -1.9848

Max Act: 1.8723. Min Act: -0.1700

Data Index: 7437285 (Open Web Text)

Max Activating Token Index: 608

Text #11

Max Range: 1.9848. Min Range: -1.9848

Max Act: 1.8414. Min Act: -0.1700

Data Index: 7241692 (Open Web Text)

Max Activating Token Index: 433

Text #12

Max Range: 1.9848. Min Range: -1.9848

Max Act: 1.8718. Min Act: -0.1698

Data Index: 5603724 (Open Web Text)

Max Activating Token Index: 115

Text #13

Max Range: 1.9848. Min Range: -1.9848

Max Act: 1.8404. Min Act: -0.1700

Data Index: 5960756 (Open Web Text)

Max Activating Token Index: 453

Text #14

Max Range: 1.9848. Min Range: -1.9848

Max Act: 1.8575. Min Act: -0.1700

Data Index: 3100112 (Open Web Text)

Max Activating Token Index: 603

Text #15

Max Range: 1.9848. Min Range: -1.9848

Max Act: 1.8316. Min Act: -0.1700

Data Index: 7970633 (Open Web Text)

Max Activating Token Index: 468

Text #16

Max Range: 1.9848. Min Range: -1.9848

Max Act: 1.8435. Min Act: -0.1700

Data Index: 4412087 (Open Web Text)

Max Activating Token Index: 858

Text #17

Max Range: 1.9848. Min Range: -1.9848

Max Act: 1.8464. Min Act: -0.1700

Data Index: 7833827 (Open Web Text)

Max Activating Token Index: 886

Text #18

Max Range: 1.9848. Min Range: -1.9848

Max Act: 1.8400. Min Act: -0.1700

Data Index: 4460663 (Open Web Text)

Max Activating Token Index: 232

Text #19

Max Range: 1.9848. Min Range: -1.9848

Max Act: 1.8283. Min Act: -0.1700

Data Index: 6460437 (Open Web Text)

Max Activating Token Index: 594