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

Dataset: Open Web Text

Neuron 1513 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: 3.4505. Min Range: -3.4505

Max Act: 3.4505. Min Act: -0.1700

Data Index: 3688432 (Open Web Text)

Max Activating Token Index: 777

Text #1

Max Range: 3.4505. Min Range: -3.4505

Max Act: 3.0529. Min Act: -0.1700

Data Index: 1567244 (Open Web Text)

Max Activating Token Index: 536

Text #2

Max Range: 3.4505. Min Range: -3.4505

Max Act: 2.9006. Min Act: -0.1700

Data Index: 2428767 (Open Web Text)

Max Activating Token Index: 679

Text #3

Max Range: 3.4505. Min Range: -3.4505

Max Act: 2.9877. Min Act: -0.1700

Data Index: 4737769 (Open Web Text)

Max Activating Token Index: 146

Text #4

Max Range: 3.4505. Min Range: -3.4505

Max Act: 2.8292. Min Act: -0.1700

Data Index: 8130466 (Open Web Text)

Max Activating Token Index: 999

Text #5

Max Range: 3.4505. Min Range: -3.4505

Max Act: 2.6757. Min Act: -0.1700

Data Index: 7732632 (Open Web Text)

Max Activating Token Index: 910

Text #6

Max Range: 3.4505. Min Range: -3.4505

Max Act: 2.7443. Min Act: -0.1700

Data Index: 2283180 (Open Web Text)

Max Activating Token Index: 415

Text #7

Max Range: 3.4505. Min Range: -3.4505

Max Act: 2.7485. Min Act: -0.1700

Data Index: 7184539 (Open Web Text)

Max Activating Token Index: 922

Text #8

Max Range: 3.4505. Min Range: -3.4505

Max Act: 2.8010. Min Act: -0.1700

Data Index: 6971183 (Open Web Text)

Max Activating Token Index: 554

Text #9

Max Range: 3.4505. Min Range: -3.4505

Max Act: 2.7604. Min Act: -0.1700

Data Index: 7331386 (Open Web Text)

Max Activating Token Index: 384

Text #10

Max Range: 3.4505. Min Range: -3.4505

Max Act: 2.7370. Min Act: -0.1700

Data Index: 6134418 (Open Web Text)

Max Activating Token Index: 510

Text #11

Max Range: 3.4505. Min Range: -3.4505

Max Act: 2.7182. Min Act: -0.1700

Data Index: 2589476 (Open Web Text)

Max Activating Token Index: 25

Text #12

Max Range: 3.4505. Min Range: -3.4505

Max Act: 2.7879. Min Act: -0.1700

Data Index: 1494308 (Open Web Text)

Max Activating Token Index: 804

Text #13

Max Range: 3.4505. Min Range: -3.4505

Max Act: 2.7251. Min Act: -0.1700

Data Index: 4316053 (Open Web Text)

Max Activating Token Index: 177

Text #14

Max Range: 3.4505. Min Range: -3.4505

Max Act: 2.7098. Min Act: -0.1700

Data Index: 7575043 (Open Web Text)

Max Activating Token Index: 286

Text #15

Max Range: 3.4505. Min Range: -3.4505

Max Act: 2.7709. Min Act: -0.1700

Data Index: 1203774 (Open Web Text)

Max Activating Token Index: 637

Text #16

Max Range: 3.4505. Min Range: -3.4505

Max Act: 2.7128. Min Act: -0.1700

Data Index: 2613885 (Open Web Text)

Max Activating Token Index: 402

Text #17

Max Range: 3.4505. Min Range: -3.4505

Max Act: 2.6886. Min Act: -0.1700

Data Index: 6902462 (Open Web Text)

Max Activating Token Index: 455

Text #18

Max Range: 3.4505. Min Range: -3.4505

Max Act: 2.7357. Min Act: -0.1700

Data Index: 3510348 (Open Web Text)

Max Activating Token Index: 656

Text #19

Max Range: 3.4505. Min Range: -3.4505

Max Act: 2.6627. Min Act: -0.1700

Data Index: 1660725 (Open Web Text)

Max Activating Token Index: 414