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

Dataset: Open Web Text

Neuron 251 in Layer 4

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: 4.8269. Min Range: -4.8269

Max Act: 4.8269. Min Act: -0.1700

Data Index: 3760714 (Open Web Text)

Max Activating Token Index: 782

Text #1

Max Range: 4.8269. Min Range: -4.8269

Max Act: 4.7983. Min Act: -0.1700

Data Index: 4345012 (Open Web Text)

Max Activating Token Index: 870

Text #2

Max Range: 4.8269. Min Range: -4.8269

Max Act: 4.8008. Min Act: -0.1700

Data Index: 4938321 (Open Web Text)

Max Activating Token Index: 289

Text #3

Max Range: 4.8269. Min Range: -4.8269

Max Act: 4.6449. Min Act: -0.1700

Data Index: 2507522 (Open Web Text)

Max Activating Token Index: 561

Text #4

Max Range: 4.8269. Min Range: -4.8269

Max Act: 4.5445. Min Act: -0.1700

Data Index: 5731937 (Open Web Text)

Max Activating Token Index: 472

Text #5

Max Range: 4.8269. Min Range: -4.8269

Max Act: 4.5540. Min Act: -0.1700

Data Index: 3173139 (Open Web Text)

Max Activating Token Index: 829

Text #6

Max Range: 4.8269. Min Range: -4.8269

Max Act: 4.5199. Min Act: -0.1700

Data Index: 8188368 (Open Web Text)

Max Activating Token Index: 898

Text #7

Max Range: 4.8269. Min Range: -4.8269

Max Act: 4.4658. Min Act: -0.1700

Data Index: 7387043 (Open Web Text)

Max Activating Token Index: 667

Text #8

Max Range: 4.8269. Min Range: -4.8269

Max Act: 4.5161. Min Act: -0.1700

Data Index: 7195065 (Open Web Text)

Max Activating Token Index: 260

Text #9

Max Range: 4.8269. Min Range: -4.8269

Max Act: 4.4714. Min Act: -0.1700

Data Index: 1227661 (Open Web Text)

Max Activating Token Index: 444

Text #10

Max Range: 4.8269. Min Range: -4.8269

Max Act: 4.5133. Min Act: -0.1700

Data Index: 1180734 (Open Web Text)

Max Activating Token Index: 915

Text #11

Max Range: 4.8269. Min Range: -4.8269

Max Act: 4.4812. Min Act: -0.1700

Data Index: 2451948 (Open Web Text)

Max Activating Token Index: 513

Text #12

Max Range: 4.8269. Min Range: -4.8269

Max Act: 4.4523. Min Act: -0.1700

Data Index: 7350478 (Open Web Text)

Max Activating Token Index: 334

Text #13

Max Range: 4.8269. Min Range: -4.8269

Max Act: 4.4592. Min Act: -0.1700

Data Index: 6482721 (Open Web Text)

Max Activating Token Index: 406

Text #14

Max Range: 4.8269. Min Range: -4.8269

Max Act: 4.4697. Min Act: -0.1700

Data Index: 750929 (Open Web Text)

Max Activating Token Index: 134

Text #15

Max Range: 4.8269. Min Range: -4.8269

Max Act: 4.4370. Min Act: -0.1700

Data Index: 8774709 (Open Web Text)

Max Activating Token Index: 337

Text #16

Max Range: 4.8269. Min Range: -4.8269

Max Act: 4.4075. Min Act: -0.1700

Data Index: 591185 (Open Web Text)

Max Activating Token Index: 737

Text #17

Max Range: 4.8269. Min Range: -4.8269

Max Act: 4.4146. Min Act: -0.1700

Data Index: 4971650 (Open Web Text)

Max Activating Token Index: 428

Text #18

Max Range: 4.8269. Min Range: -4.8269

Max Act: 4.4333. Min Act: -0.1700

Data Index: 6924327 (Open Web Text)

Max Activating Token Index: 881

Text #19

Max Range: 4.8269. Min Range: -4.8269

Max Act: 4.4291. Min Act: -0.1700

Data Index: 7106619 (Open Web Text)

Max Activating Token Index: 880