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

Dataset: Open Web Text

Neuron 2562 in Layer 0

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: 2.9388. Min Range: -2.9388

Max Act: 2.9388. Min Act: -0.1700

Data Index: 5065768 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.9388. Min Range: -2.9388

Max Act: 2.8127. Min Act: -0.1700

Data Index: 6206802 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.9388. Min Range: -2.9388

Max Act: 2.7991. Min Act: -0.1700

Data Index: 4091110 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 2.9388. Min Range: -2.9388

Max Act: 2.8091. Min Act: -0.1700

Data Index: 1333561 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.9388. Min Range: -2.9388

Max Act: 2.7872. Min Act: -0.1700

Data Index: 8232158 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 2.9388. Min Range: -2.9388

Max Act: 2.7644. Min Act: -0.1700

Data Index: 4768832 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.9388. Min Range: -2.9388

Max Act: 2.7788. Min Act: -0.1700

Data Index: 6653262 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 2.9388. Min Range: -2.9388

Max Act: 2.7756. Min Act: -0.1700

Data Index: 1715780 (Open Web Text)

Max Activating Token Index: 20

Text #8

Max Range: 2.9388. Min Range: -2.9388

Max Act: 2.7557. Min Act: -0.1700

Data Index: 4321770 (Open Web Text)

Max Activating Token Index: 20

Text #9

Max Range: 2.9388. Min Range: -2.9388

Max Act: 2.7545. Min Act: -0.1700

Data Index: 2044787 (Open Web Text)

Max Activating Token Index: 13

Text #10

Max Range: 2.9388. Min Range: -2.9388

Max Act: 2.7573. Min Act: -0.1700

Data Index: 6717299 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 2.9388. Min Range: -2.9388

Max Act: 2.7371. Min Act: -0.1700

Data Index: 7659601 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 2.9388. Min Range: -2.9388

Max Act: 2.7388. Min Act: -0.1700

Data Index: 7770467 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.9388. Min Range: -2.9388

Max Act: 2.7395. Min Act: -0.1700

Data Index: 2557235 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 2.9388. Min Range: -2.9388

Max Act: 2.7302. Min Act: -0.1700

Data Index: 6533323 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 2.9388. Min Range: -2.9388

Max Act: 2.7195. Min Act: -0.1700

Data Index: 7032723 (Open Web Text)

Max Activating Token Index: 577

Text #16

Max Range: 2.9388. Min Range: -2.9388

Max Act: 2.7256. Min Act: -0.1700

Data Index: 7272759 (Open Web Text)

Max Activating Token Index: 667

Text #17

Max Range: 2.9388. Min Range: -2.9388

Max Act: 2.7194. Min Act: -0.1700

Data Index: 5750722 (Open Web Text)

Max Activating Token Index: 566

Text #18

Max Range: 2.9388. Min Range: -2.9388

Max Act: 2.7212. Min Act: -0.1700

Data Index: 7517455 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 2.9388. Min Range: -2.9388

Max Act: 2.7283. Min Act: -0.1700

Data Index: 2418038 (Open Web Text)

Max Activating Token Index: 697