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

Dataset: Open Web Text

Neuron 302 in Layer 0

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: 2.4403. Min Range: -2.4403

Max Act: 2.4403. Min Act: -0.1700

Data Index: 5027797 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 2.4403. Min Range: -2.4403

Max Act: 2.3711. Min Act: -0.1700

Data Index: 5619803 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.4403. Min Range: -2.4403

Max Act: 2.3592. Min Act: -0.1700

Data Index: 3716752 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 2.4403. Min Range: -2.4403

Max Act: 2.3606. Min Act: -0.1700

Data Index: 5240477 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 2.4403. Min Range: -2.4403

Max Act: 2.3508. Min Act: -0.1700

Data Index: 1108227 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 2.4403. Min Range: -2.4403

Max Act: 2.3345. Min Act: -0.1699

Data Index: 6387898 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 2.4403. Min Range: -2.4403

Max Act: 2.3386. Min Act: -0.1700

Data Index: 20025 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 2.4403. Min Range: -2.4403

Max Act: 2.3403. Min Act: -0.1700

Data Index: 2579999 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.4403. Min Range: -2.4403

Max Act: 2.3479. Min Act: -0.1698

Data Index: 5484443 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 2.4403. Min Range: -2.4403

Max Act: 2.3338. Min Act: -0.1700

Data Index: 2219699 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 2.4403. Min Range: -2.4403

Max Act: 2.3319. Min Act: -0.1700

Data Index: 3702473 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 2.4403. Min Range: -2.4403

Max Act: 2.3342. Min Act: -0.1700

Data Index: 7700461 (Open Web Text)

Max Activating Token Index: 30

Text #12

Max Range: 2.4403. Min Range: -2.4403

Max Act: 2.3458. Min Act: -0.1700

Data Index: 1905879 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 2.4403. Min Range: -2.4403

Max Act: 2.3315. Min Act: -0.1700

Data Index: 6595584 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 2.4403. Min Range: -2.4403

Max Act: 2.3390. Min Act: -0.1700

Data Index: 2898589 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 2.4403. Min Range: -2.4403

Max Act: 2.3338. Min Act: -0.1700

Data Index: 796681 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 2.4403. Min Range: -2.4403

Max Act: 2.3175. Min Act: -0.1700

Data Index: 1963358 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.4403. Min Range: -2.4403

Max Act: 2.3166. Min Act: -0.1699

Data Index: 1222816 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 2.4403. Min Range: -2.4403

Max Act: 2.3214. Min Act: -0.1700

Data Index: 5507414 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 2.4403. Min Range: -2.4403

Max Act: 2.3160. Min Act: -0.1700

Data Index: 5743269 (Open Web Text)

Max Activating Token Index: 8