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

Dataset: Open Web Text

Neuron 1295 in Layer 5

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: 4.5444. Min Range: -4.5444

Max Act: 4.5444. Min Act: -0.1700

Data Index: 8257386 (Open Web Text)

Max Activating Token Index: 468

Text #1

Max Range: 4.5444. Min Range: -4.5444

Max Act: 4.4510. Min Act: -0.1700

Data Index: 3226441 (Open Web Text)

Max Activating Token Index: 839

Text #2

Max Range: 4.5444. Min Range: -4.5444

Max Act: 4.4317. Min Act: -0.1700

Data Index: 653293 (Open Web Text)

Max Activating Token Index: 863

Text #3

Max Range: 4.5444. Min Range: -4.5444

Max Act: 4.4125. Min Act: -0.1700

Data Index: 5920413 (Open Web Text)

Max Activating Token Index: 760

Text #4

Max Range: 4.5444. Min Range: -4.5444

Max Act: 4.4342. Min Act: -0.1700

Data Index: 1334892 (Open Web Text)

Max Activating Token Index: 758

Text #5

Max Range: 4.5444. Min Range: -4.5444

Max Act: 4.4413. Min Act: -0.1700

Data Index: 413777 (Open Web Text)

Max Activating Token Index: 429

Text #6

Max Range: 4.5444. Min Range: -4.5444

Max Act: 4.3787. Min Act: -0.1700

Data Index: 7122105 (Open Web Text)

Max Activating Token Index: 165

Text #7

Max Range: 4.5444. Min Range: -4.5444

Max Act: 4.3711. Min Act: -0.1700

Data Index: 2518250 (Open Web Text)

Max Activating Token Index: 437

Text #8

Max Range: 4.5444. Min Range: -4.5444

Max Act: 4.3945. Min Act: -0.1700

Data Index: 2153160 (Open Web Text)

Max Activating Token Index: 872

Text #9

Max Range: 4.5444. Min Range: -4.5444

Max Act: 4.3847. Min Act: -0.1700

Data Index: 4327055 (Open Web Text)

Max Activating Token Index: 307

Text #10

Max Range: 4.5444. Min Range: -4.5444

Max Act: 4.3703. Min Act: -0.1700

Data Index: 6704759 (Open Web Text)

Max Activating Token Index: 207

Text #11

Max Range: 4.5444. Min Range: -4.5444

Max Act: 4.3609. Min Act: -0.1700

Data Index: 1398667 (Open Web Text)

Max Activating Token Index: 549

Text #12

Max Range: 4.5444. Min Range: -4.5444

Max Act: 4.3683. Min Act: -0.1700

Data Index: 3470496 (Open Web Text)

Max Activating Token Index: 755

Text #13

Max Range: 4.5444. Min Range: -4.5444

Max Act: 4.3758. Min Act: -0.1700

Data Index: 6554455 (Open Web Text)

Max Activating Token Index: 814

Text #14

Max Range: 4.5444. Min Range: -4.5444

Max Act: 4.3428. Min Act: -0.1700

Data Index: 6321303 (Open Web Text)

Max Activating Token Index: 989

Text #15

Max Range: 4.5444. Min Range: -4.5444

Max Act: 4.3256. Min Act: -0.1700

Data Index: 1973871 (Open Web Text)

Max Activating Token Index: 553

Text #16

Max Range: 4.5444. Min Range: -4.5444

Max Act: 4.3429. Min Act: -0.1700

Data Index: 1291124 (Open Web Text)

Max Activating Token Index: 926

Text #17

Max Range: 4.5444. Min Range: -4.5444

Max Act: 4.3427. Min Act: -0.1700

Data Index: 5817967 (Open Web Text)

Max Activating Token Index: 597

Text #18

Max Range: 4.5444. Min Range: -4.5444

Max Act: 4.3426. Min Act: -0.1700

Data Index: 783189 (Open Web Text)

Max Activating Token Index: 489

Text #19

Max Range: 4.5444. Min Range: -4.5444

Max Act: 4.3205. Min Act: -0.1700

Data Index: 2694819 (Open Web Text)

Max Activating Token Index: 204