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

Dataset: Open Web Text

Neuron 969 in Layer 1

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: 2.3655. Min Range: -2.3655

Max Act: 2.3655. Min Act: -0.1700

Data Index: 8187832 (Open Web Text)

Max Activating Token Index: 507

Text #1

Max Range: 2.3655. Min Range: -2.3655

Max Act: 2.3025. Min Act: -0.1700

Data Index: 2015407 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 2.3655. Min Range: -2.3655

Max Act: 2.2524. Min Act: -0.1700

Data Index: 4667769 (Open Web Text)

Max Activating Token Index: 31

Text #3

Max Range: 2.3655. Min Range: -2.3655

Max Act: 2.2748. Min Act: -0.1700

Data Index: 1214436 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 2.3655. Min Range: -2.3655

Max Act: 2.2425. Min Act: -0.1700

Data Index: 1467081 (Open Web Text)

Max Activating Token Index: 321

Text #5

Max Range: 2.3655. Min Range: -2.3655

Max Act: 2.2611. Min Act: -0.1700

Data Index: 1120799 (Open Web Text)

Max Activating Token Index: 418

Text #6

Max Range: 2.3655. Min Range: -2.3655

Max Act: 2.2508. Min Act: -0.1700

Data Index: 3493423 (Open Web Text)

Max Activating Token Index: 25

Text #7

Max Range: 2.3655. Min Range: -2.3655

Max Act: 2.2546. Min Act: -0.1700

Data Index: 6078187 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 2.3655. Min Range: -2.3655

Max Act: 2.2587. Min Act: -0.1700

Data Index: 8828136 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 2.3655. Min Range: -2.3655

Max Act: 2.2562. Min Act: -0.1700

Data Index: 1024833 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 2.3655. Min Range: -2.3655

Max Act: 2.2224. Min Act: -0.1700

Data Index: 2136810 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.3655. Min Range: -2.3655

Max Act: 2.2313. Min Act: -0.1700

Data Index: 3773732 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.3655. Min Range: -2.3655

Max Act: 2.2288. Min Act: -0.1700

Data Index: 866282 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.3655. Min Range: -2.3655

Max Act: 2.2188. Min Act: -0.1700

Data Index: 3930897 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 2.3655. Min Range: -2.3655

Max Act: 2.2277. Min Act: -0.1700

Data Index: 7050970 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 2.3655. Min Range: -2.3655

Max Act: 2.2422. Min Act: -0.1700

Data Index: 2559880 (Open Web Text)

Max Activating Token Index: 185

Text #16

Max Range: 2.3655. Min Range: -2.3655

Max Act: 2.2494. Min Act: -0.1700

Data Index: 6606740 (Open Web Text)

Max Activating Token Index: 509

Text #17

Max Range: 2.3655. Min Range: -2.3655

Max Act: 2.2108. Min Act: -0.1700

Data Index: 6565990 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 2.3655. Min Range: -2.3655

Max Act: 2.2210. Min Act: -0.1700

Data Index: 2929100 (Open Web Text)

Max Activating Token Index: 13

Text #19

Max Range: 2.3655. Min Range: -2.3655

Max Act: 2.2141. Min Act: -0.1700

Data Index: 1436395 (Open Web Text)

Max Activating Token Index: 23