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

Dataset: Open Web Text

Neuron 1026 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: 4.3445. Min Range: -4.3445

Max Act: 4.3445. Min Act: -0.1700

Data Index: 8422529 (Open Web Text)

Max Activating Token Index: 445

Text #1

Max Range: 4.3445. Min Range: -4.3445

Max Act: 4.3178. Min Act: -0.1700

Data Index: 3897196 (Open Web Text)

Max Activating Token Index: 64

Text #2

Max Range: 4.3445. Min Range: -4.3445

Max Act: 4.2811. Min Act: -0.1700

Data Index: 1521179 (Open Web Text)

Max Activating Token Index: 635

Text #3

Max Range: 4.3445. Min Range: -4.3445

Max Act: 4.3156. Min Act: -0.1700

Data Index: 5590531 (Open Web Text)

Max Activating Token Index: 564

Text #4

Max Range: 4.3445. Min Range: -4.3445

Max Act: 4.2637. Min Act: -0.1700

Data Index: 7938464 (Open Web Text)

Max Activating Token Index: 327

Text #5

Max Range: 4.3445. Min Range: -4.3445

Max Act: 4.2088. Min Act: -0.1700

Data Index: 6471960 (Open Web Text)

Max Activating Token Index: 715

Text #6

Max Range: 4.3445. Min Range: -4.3445

Max Act: 4.2006. Min Act: -0.1700

Data Index: 7625330 (Open Web Text)

Max Activating Token Index: 782

Text #7

Max Range: 4.3445. Min Range: -4.3445

Max Act: 4.1807. Min Act: -0.1700

Data Index: 6792150 (Open Web Text)

Max Activating Token Index: 799

Text #8

Max Range: 4.3445. Min Range: -4.3445

Max Act: 4.1518. Min Act: -0.1700

Data Index: 8436470 (Open Web Text)

Max Activating Token Index: 864

Text #9

Max Range: 4.3445. Min Range: -4.3445

Max Act: 4.1325. Min Act: -0.1700

Data Index: 3595876 (Open Web Text)

Max Activating Token Index: 386

Text #10

Max Range: 4.3445. Min Range: -4.3445

Max Act: 4.1515. Min Act: -0.1700

Data Index: 1863924 (Open Web Text)

Max Activating Token Index: 464

Text #11

Max Range: 4.3445. Min Range: -4.3445

Max Act: 4.1521. Min Act: -0.1700

Data Index: 7951263 (Open Web Text)

Max Activating Token Index: 101

Text #12

Max Range: 4.3445. Min Range: -4.3445

Max Act: 4.1529. Min Act: -0.1700

Data Index: 5470389 (Open Web Text)

Max Activating Token Index: 621

Text #13

Max Range: 4.3445. Min Range: -4.3445

Max Act: 4.1302. Min Act: -0.1700

Data Index: 273885 (Open Web Text)

Max Activating Token Index: 461

Text #14

Max Range: 4.3445. Min Range: -4.3445

Max Act: 4.1487. Min Act: -0.1700

Data Index: 4592511 (Open Web Text)

Max Activating Token Index: 492

Text #15

Max Range: 4.3445. Min Range: -4.3445

Max Act: 4.1339. Min Act: -0.1700

Data Index: 6009304 (Open Web Text)

Max Activating Token Index: 520

Text #16

Max Range: 4.3445. Min Range: -4.3445

Max Act: 4.1192. Min Act: -0.1700

Data Index: 699645 (Open Web Text)

Max Activating Token Index: 893

Text #17

Max Range: 4.3445. Min Range: -4.3445

Max Act: 4.1165. Min Act: -0.1700

Data Index: 5583814 (Open Web Text)

Max Activating Token Index: 463

Text #18

Max Range: 4.3445. Min Range: -4.3445

Max Act: 4.0985. Min Act: -0.1700

Data Index: 3874004 (Open Web Text)

Max Activating Token Index: 214

Text #19

Max Range: 4.3445. Min Range: -4.3445

Max Act: 4.1244. Min Act: -0.1700

Data Index: 501080 (Open Web Text)

Max Activating Token Index: 645