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

Dataset: Open Web Text

Neuron 2752 in Layer 2

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: 3.5503. Min Range: -3.5503

Max Act: 3.5503. Min Act: -0.1700

Data Index: 8743848 (Open Web Text)

Max Activating Token Index: 38

Text #1

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.5226. Min Act: -0.1700

Data Index: 5905503 (Open Web Text)

Max Activating Token Index: 933

Text #2

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.4925. Min Act: -0.1700

Data Index: 1246070 (Open Web Text)

Max Activating Token Index: 438

Text #3

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.4800. Min Act: -0.1700

Data Index: 7395646 (Open Web Text)

Max Activating Token Index: 634

Text #4

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.4636. Min Act: -0.1700

Data Index: 8780917 (Open Web Text)

Max Activating Token Index: 518

Text #5

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.4177. Min Act: -0.1700

Data Index: 6525530 (Open Web Text)

Max Activating Token Index: 406

Text #6

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.3987. Min Act: -0.1700

Data Index: 3951250 (Open Web Text)

Max Activating Token Index: 760

Text #7

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.3829. Min Act: -0.1700

Data Index: 6976788 (Open Web Text)

Max Activating Token Index: 608

Text #8

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.3987. Min Act: -0.1700

Data Index: 220774 (Open Web Text)

Max Activating Token Index: 622

Text #9

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.4033. Min Act: -0.1700

Data Index: 4765832 (Open Web Text)

Max Activating Token Index: 389

Text #10

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.3725. Min Act: -0.1700

Data Index: 3688204 (Open Web Text)

Max Activating Token Index: 760

Text #11

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.3770. Min Act: -0.1700

Data Index: 3790752 (Open Web Text)

Max Activating Token Index: 96

Text #12

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.3731. Min Act: -0.1700

Data Index: 287004 (Open Web Text)

Max Activating Token Index: 86

Text #13

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.3770. Min Act: -0.1700

Data Index: 6514407 (Open Web Text)

Max Activating Token Index: 662

Text #14

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.3623. Min Act: -0.1700

Data Index: 4797049 (Open Web Text)

Max Activating Token Index: 894

Text #15

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.3657. Min Act: -0.1700

Data Index: 5566049 (Open Web Text)

Max Activating Token Index: 220

Text #16

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.3627. Min Act: -0.1700

Data Index: 5804854 (Open Web Text)

Max Activating Token Index: 746

Text #17

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.3514. Min Act: -0.1700

Data Index: 7165144 (Open Web Text)

Max Activating Token Index: 65

Text #18

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.3571. Min Act: -0.1700

Data Index: 5788363 (Open Web Text)

Max Activating Token Index: 66

Text #19

Max Range: 3.5503. Min Range: -3.5503

Max Act: 3.3508. Min Act: -0.1700

Data Index: 593279 (Open Web Text)

Max Activating Token Index: 182