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

Dataset: Open Web Text

Neuron 2774 in Layer 2

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: 5.7528. Min Range: -5.7528

Max Act: 5.7528. Min Act: -0.1700

Data Index: 2725834 (Open Web Text)

Max Activating Token Index: 370

Text #1

Max Range: 5.7528. Min Range: -5.7528

Max Act: 5.7340. Min Act: -0.1700

Data Index: 5489397 (Open Web Text)

Max Activating Token Index: 206

Text #2

Max Range: 5.7528. Min Range: -5.7528

Max Act: 5.6980. Min Act: -0.1700

Data Index: 7370562 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 5.7528. Min Range: -5.7528

Max Act: 5.7234. Min Act: -0.1700

Data Index: 6073272 (Open Web Text)

Max Activating Token Index: 834

Text #4

Max Range: 5.7528. Min Range: -5.7528

Max Act: 5.7284. Min Act: -0.1700

Data Index: 395024 (Open Web Text)

Max Activating Token Index: 13

Text #5

Max Range: 5.7528. Min Range: -5.7528

Max Act: 5.7133. Min Act: -0.1700

Data Index: 202818 (Open Web Text)

Max Activating Token Index: 197

Text #6

Max Range: 5.7528. Min Range: -5.7528

Max Act: 5.6971. Min Act: -0.1700

Data Index: 8562843 (Open Web Text)

Max Activating Token Index: 367

Text #7

Max Range: 5.7528. Min Range: -5.7528

Max Act: 5.7046. Min Act: -0.1700

Data Index: 1393188 (Open Web Text)

Max Activating Token Index: 724

Text #8

Max Range: 5.7528. Min Range: -5.7528

Max Act: 5.6607. Min Act: -0.1700

Data Index: 3882446 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 5.7528. Min Range: -5.7528

Max Act: 5.6776. Min Act: -0.1700

Data Index: 563393 (Open Web Text)

Max Activating Token Index: 157

Text #10

Max Range: 5.7528. Min Range: -5.7528

Max Act: 5.6856. Min Act: -0.1700

Data Index: 2361685 (Open Web Text)

Max Activating Token Index: 559

Text #11

Max Range: 5.7528. Min Range: -5.7528

Max Act: 5.6831. Min Act: -0.1700

Data Index: 5816059 (Open Web Text)

Max Activating Token Index: 540

Text #12

Max Range: 5.7528. Min Range: -5.7528

Max Act: 5.6768. Min Act: -0.1700

Data Index: 314620 (Open Web Text)

Max Activating Token Index: 347

Text #13

Max Range: 5.7528. Min Range: -5.7528

Max Act: 5.6742. Min Act: -0.1700

Data Index: 4131515 (Open Web Text)

Max Activating Token Index: 151

Text #14

Max Range: 5.7528. Min Range: -5.7528

Max Act: 5.6383. Min Act: -0.1700

Data Index: 4585770 (Open Web Text)

Max Activating Token Index: 103

Text #15

Max Range: 5.7528. Min Range: -5.7528

Max Act: 5.6337. Min Act: -0.1700

Data Index: 4773637 (Open Web Text)

Max Activating Token Index: 355

Text #16

Max Range: 5.7528. Min Range: -5.7528

Max Act: 5.6424. Min Act: -0.1700

Data Index: 113085 (Open Web Text)

Max Activating Token Index: 20

Text #17

Max Range: 5.7528. Min Range: -5.7528

Max Act: 5.6533. Min Act: -0.1700

Data Index: 1286861 (Open Web Text)

Max Activating Token Index: 396

Text #18

Max Range: 5.7528. Min Range: -5.7528

Max Act: 5.6552. Min Act: -0.1700

Data Index: 5518657 (Open Web Text)

Max Activating Token Index: 868

Text #19

Max Range: 5.7528. Min Range: -5.7528

Max Act: 5.6514. Min Act: -0.1700

Data Index: 5948420 (Open Web Text)

Max Activating Token Index: 502