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

Dataset: Open Web Text

Neuron 520 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: 3.7753. Min Range: -3.7753

Max Act: 3.7579. Min Act: -0.1700

Data Index: 6103774 (Open Web Text)

Max Activating Token Index: 330

Text #1

Max Range: 3.7753. Min Range: -3.7753

Max Act: 3.7626. Min Act: -0.1700

Data Index: 6003643 (Open Web Text)

Max Activating Token Index: 403

Text #2

Max Range: 3.7753. Min Range: -3.7753

Max Act: 3.7753. Min Act: -0.1700

Data Index: 1932079 (Open Web Text)

Max Activating Token Index: 560

Text #3

Max Range: 3.7753. Min Range: -3.7753

Max Act: 3.7608. Min Act: -0.1700

Data Index: 3807235 (Open Web Text)

Max Activating Token Index: 292

Text #4

Max Range: 3.7753. Min Range: -3.7753

Max Act: 3.7394. Min Act: -0.1700

Data Index: 2707651 (Open Web Text)

Max Activating Token Index: 615

Text #5

Max Range: 3.7753. Min Range: -3.7753

Max Act: 3.7326. Min Act: -0.1700

Data Index: 7318922 (Open Web Text)

Max Activating Token Index: 595

Text #6

Max Range: 3.7753. Min Range: -3.7753

Max Act: 3.6977. Min Act: -0.1700

Data Index: 5160130 (Open Web Text)

Max Activating Token Index: 1013

Text #7

Max Range: 3.7753. Min Range: -3.7753

Max Act: 3.7067. Min Act: -0.1700

Data Index: 2700932 (Open Web Text)

Max Activating Token Index: 330

Text #8

Max Range: 3.7753. Min Range: -3.7753

Max Act: 3.6536. Min Act: -0.1700

Data Index: 8261123 (Open Web Text)

Max Activating Token Index: 295

Text #9

Max Range: 3.7753. Min Range: -3.7753

Max Act: 3.6785. Min Act: -0.1700

Data Index: 3961317 (Open Web Text)

Max Activating Token Index: 645

Text #10

Max Range: 3.7753. Min Range: -3.7753

Max Act: 3.6532. Min Act: -0.1700

Data Index: 3259673 (Open Web Text)

Max Activating Token Index: 678

Text #11

Max Range: 3.7753. Min Range: -3.7753

Max Act: 3.6383. Min Act: -0.1700

Data Index: 4697514 (Open Web Text)

Max Activating Token Index: 540

Text #12

Max Range: 3.7753. Min Range: -3.7753

Max Act: 3.6411. Min Act: -0.1700

Data Index: 7562756 (Open Web Text)

Max Activating Token Index: 180

Text #13

Max Range: 3.7753. Min Range: -3.7753

Max Act: 3.6226. Min Act: -0.1700

Data Index: 7285353 (Open Web Text)

Max Activating Token Index: 386

Text #14

Max Range: 3.7753. Min Range: -3.7753

Max Act: 3.6355. Min Act: -0.1700

Data Index: 6003641 (Open Web Text)

Max Activating Token Index: 725

Text #15

Max Range: 3.7753. Min Range: -3.7753

Max Act: 3.6378. Min Act: -0.1700

Data Index: 1488631 (Open Web Text)

Max Activating Token Index: 345

Text #16

Max Range: 3.7753. Min Range: -3.7753

Max Act: 3.6470. Min Act: -0.1700

Data Index: 1932087 (Open Web Text)

Max Activating Token Index: 557

Text #17

Max Range: 3.7753. Min Range: -3.7753

Max Act: 3.6473. Min Act: -0.1700

Data Index: 2247996 (Open Web Text)

Max Activating Token Index: 713

Text #18

Max Range: 3.7753. Min Range: -3.7753

Max Act: 3.6261. Min Act: -0.1700

Data Index: 6766401 (Open Web Text)

Max Activating Token Index: 680

Text #19

Max Range: 3.7753. Min Range: -3.7753

Max Act: 3.6255. Min Act: -0.1700

Data Index: 8738752 (Open Web Text)

Max Activating Token Index: 575