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

Dataset: Open Web Text

Neuron 712 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: 4.0485. Min Range: -4.0485

Max Act: 4.0485. Min Act: -0.1700

Data Index: 3987084 (Open Web Text)

Max Activating Token Index: 1007

Text #1

Max Range: 4.0485. Min Range: -4.0485

Max Act: 3.9869. Min Act: -0.1700

Data Index: 2349386 (Open Web Text)

Max Activating Token Index: 374

Text #2

Max Range: 4.0485. Min Range: -4.0485

Max Act: 3.9255. Min Act: -0.1700

Data Index: 6113991 (Open Web Text)

Max Activating Token Index: 742

Text #3

Max Range: 4.0485. Min Range: -4.0485

Max Act: 3.9373. Min Act: -0.1700

Data Index: 7604273 (Open Web Text)

Max Activating Token Index: 62

Text #4

Max Range: 4.0485. Min Range: -4.0485

Max Act: 3.9385. Min Act: -0.1700

Data Index: 8181554 (Open Web Text)

Max Activating Token Index: 319

Text #5

Max Range: 4.0485. Min Range: -4.0485

Max Act: 3.9180. Min Act: -0.1700

Data Index: 8322128 (Open Web Text)

Max Activating Token Index: 123

Text #6

Max Range: 4.0485. Min Range: -4.0485

Max Act: 3.8818. Min Act: -0.1700

Data Index: 7610215 (Open Web Text)

Max Activating Token Index: 327

Text #7

Max Range: 4.0485. Min Range: -4.0485

Max Act: 3.8759. Min Act: -0.1700

Data Index: 6113990 (Open Web Text)

Max Activating Token Index: 853

Text #8

Max Range: 4.0485. Min Range: -4.0485

Max Act: 3.8636. Min Act: -0.1700

Data Index: 4769475 (Open Web Text)

Max Activating Token Index: 841

Text #9

Max Range: 4.0485. Min Range: -4.0485

Max Act: 3.8513. Min Act: -0.1700

Data Index: 5145598 (Open Web Text)

Max Activating Token Index: 461

Text #10

Max Range: 4.0485. Min Range: -4.0485

Max Act: 3.8579. Min Act: -0.1700

Data Index: 8347413 (Open Web Text)

Max Activating Token Index: 226

Text #11

Max Range: 4.0485. Min Range: -4.0485

Max Act: 3.8667. Min Act: -0.1700

Data Index: 3651190 (Open Web Text)

Max Activating Token Index: 976

Text #12

Max Range: 4.0485. Min Range: -4.0485

Max Act: 3.8068. Min Act: -0.1700

Data Index: 3307931 (Open Web Text)

Max Activating Token Index: 321

Text #13

Max Range: 4.0485. Min Range: -4.0485

Max Act: 3.8402. Min Act: -0.1700

Data Index: 2355942 (Open Web Text)

Max Activating Token Index: 379

Text #14

Max Range: 4.0485. Min Range: -4.0485

Max Act: 3.7947. Min Act: -0.1700

Data Index: 115245 (Open Web Text)

Max Activating Token Index: 349

Text #15

Max Range: 4.0485. Min Range: -4.0485

Max Act: 3.7794. Min Act: -0.1700

Data Index: 628636 (Open Web Text)

Max Activating Token Index: 1020

Text #16

Max Range: 4.0485. Min Range: -4.0485

Max Act: 3.8194. Min Act: -0.1700

Data Index: 93164 (Open Web Text)

Max Activating Token Index: 508

Text #17

Max Range: 4.0485. Min Range: -4.0485

Max Act: 3.8231. Min Act: -0.1700

Data Index: 5403538 (Open Web Text)

Max Activating Token Index: 65

Text #18

Max Range: 4.0485. Min Range: -4.0485

Max Act: 3.8053. Min Act: -0.1700

Data Index: 5426972 (Open Web Text)

Max Activating Token Index: 184

Text #19

Max Range: 4.0485. Min Range: -4.0485

Max Act: 3.7970. Min Act: -0.1700

Data Index: 5950277 (Open Web Text)

Max Activating Token Index: 838