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

Dataset: Open Web Text

Neuron 2521 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: 3.3723. Min Range: -3.3723

Max Act: 3.3723. Min Act: -0.1700

Data Index: 5797391 (Open Web Text)

Max Activating Token Index: 472

Text #1

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.2195. Min Act: -0.1700

Data Index: 4642385 (Open Web Text)

Max Activating Token Index: 60

Text #2

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.1789. Min Act: -0.1700

Data Index: 8793440 (Open Web Text)

Max Activating Token Index: 391

Text #3

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.2081. Min Act: -0.1700

Data Index: 4382729 (Open Web Text)

Max Activating Token Index: 762

Text #4

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.1643. Min Act: -0.1700

Data Index: 534219 (Open Web Text)

Max Activating Token Index: 828

Text #5

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.1534. Min Act: -0.1700

Data Index: 5767707 (Open Web Text)

Max Activating Token Index: 505

Text #6

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.1216. Min Act: -0.1700

Data Index: 3174974 (Open Web Text)

Max Activating Token Index: 835

Text #7

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.1218. Min Act: -0.1700

Data Index: 6864035 (Open Web Text)

Max Activating Token Index: 433

Text #8

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.1386. Min Act: -0.1700

Data Index: 6726555 (Open Web Text)

Max Activating Token Index: 411

Text #9

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.1004. Min Act: -0.1700

Data Index: 1502520 (Open Web Text)

Max Activating Token Index: 250

Text #10

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.0232. Min Act: -0.1700

Data Index: 5166457 (Open Web Text)

Max Activating Token Index: 116

Text #11

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.0507. Min Act: -0.1700

Data Index: 5326212 (Open Web Text)

Max Activating Token Index: 473

Text #12

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.0353. Min Act: -0.1700

Data Index: 8590719 (Open Web Text)

Max Activating Token Index: 680

Text #13

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.0236. Min Act: -0.1700

Data Index: 418314 (Open Web Text)

Max Activating Token Index: 960

Text #14

Max Range: 3.3723. Min Range: -3.3723

Max Act: 2.9907. Min Act: -0.1700

Data Index: 5465060 (Open Web Text)

Max Activating Token Index: 385

Text #15

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.0371. Min Act: -0.1700

Data Index: 8540978 (Open Web Text)

Max Activating Token Index: 184

Text #16

Max Range: 3.3723. Min Range: -3.3723

Max Act: 3.0023. Min Act: -0.1700

Data Index: 7714464 (Open Web Text)

Max Activating Token Index: 396

Text #17

Max Range: 3.3723. Min Range: -3.3723

Max Act: 2.9681. Min Act: -0.1700

Data Index: 1031905 (Open Web Text)

Max Activating Token Index: 802

Text #18

Max Range: 3.3723. Min Range: -3.3723

Max Act: 2.9642. Min Act: -0.1700

Data Index: 3699544 (Open Web Text)

Max Activating Token Index: 743

Text #19

Max Range: 3.3723. Min Range: -3.3723

Max Act: 2.9779. Min Act: -0.1700

Data Index: 6394001 (Open Web Text)

Max Activating Token Index: 176