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

Dataset: Open Web Text

Neuron 1524 in Layer 6

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: 4.3621. Min Range: -4.3621

Max Act: 4.3621. Min Act: -0.1700

Data Index: 5196780 (Open Web Text)

Max Activating Token Index: 152

Text #1

Max Range: 4.3621. Min Range: -4.3621

Max Act: 4.2456. Min Act: -0.1700

Data Index: 3732863 (Open Web Text)

Max Activating Token Index: 657

Text #2

Max Range: 4.3621. Min Range: -4.3621

Max Act: 4.1442. Min Act: -0.1700

Data Index: 6526123 (Open Web Text)

Max Activating Token Index: 376

Text #3

Max Range: 4.3621. Min Range: -4.3621

Max Act: 3.9624. Min Act: -0.1700

Data Index: 6460449 (Open Web Text)

Max Activating Token Index: 818

Text #4

Max Range: 4.3621. Min Range: -4.3621

Max Act: 3.9592. Min Act: -0.1700

Data Index: 3117344 (Open Web Text)

Max Activating Token Index: 416

Text #5

Max Range: 4.3621. Min Range: -4.3621

Max Act: 3.9381. Min Act: -0.1700

Data Index: 3380600 (Open Web Text)

Max Activating Token Index: 124

Text #6

Max Range: 4.3621. Min Range: -4.3621

Max Act: 3.9025. Min Act: -0.1700

Data Index: 2511797 (Open Web Text)

Max Activating Token Index: 865

Text #7

Max Range: 4.3621. Min Range: -4.3621

Max Act: 3.8938. Min Act: -0.1700

Data Index: 4124556 (Open Web Text)

Max Activating Token Index: 492

Text #8

Max Range: 4.3621. Min Range: -4.3621

Max Act: 3.9025. Min Act: -0.1700

Data Index: 2192556 (Open Web Text)

Max Activating Token Index: 718

Text #9

Max Range: 4.3621. Min Range: -4.3621

Max Act: 3.8901. Min Act: -0.1700

Data Index: 3909739 (Open Web Text)

Max Activating Token Index: 566

Text #10

Max Range: 4.3621. Min Range: -4.3621

Max Act: 3.9071. Min Act: -0.1700

Data Index: 4323462 (Open Web Text)

Max Activating Token Index: 995

Text #11

Max Range: 4.3621. Min Range: -4.3621

Max Act: 3.8776. Min Act: -0.1700

Data Index: 6081647 (Open Web Text)

Max Activating Token Index: 516

Text #12

Max Range: 4.3621. Min Range: -4.3621

Max Act: 3.8417. Min Act: -0.1700

Data Index: 1585026 (Open Web Text)

Max Activating Token Index: 378

Text #13

Max Range: 4.3621. Min Range: -4.3621

Max Act: 3.8300. Min Act: -0.1700

Data Index: 6326084 (Open Web Text)

Max Activating Token Index: 450

Text #14

Max Range: 4.3621. Min Range: -4.3621

Max Act: 3.8515. Min Act: -0.1700

Data Index: 4087030 (Open Web Text)

Max Activating Token Index: 49

Text #15

Max Range: 4.3621. Min Range: -4.3621

Max Act: 3.8453. Min Act: -0.1700

Data Index: 4762562 (Open Web Text)

Max Activating Token Index: 235

Text #16

Max Range: 4.3621. Min Range: -4.3621

Max Act: 3.8542. Min Act: -0.1700

Data Index: 3687561 (Open Web Text)

Max Activating Token Index: 459

Text #17

Max Range: 4.3621. Min Range: -4.3621

Max Act: 3.8649. Min Act: -0.1700

Data Index: 7024725 (Open Web Text)

Max Activating Token Index: 519

Text #18

Max Range: 4.3621. Min Range: -4.3621

Max Act: 3.8514. Min Act: -0.1700

Data Index: 1848051 (Open Web Text)

Max Activating Token Index: 508

Text #19

Max Range: 4.3621. Min Range: -4.3621

Max Act: 3.8279. Min Act: -0.1700

Data Index: 997882 (Open Web Text)

Max Activating Token Index: 759