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

Dataset: Open Web Text

Neuron 1774 in Layer 5

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: 3.5264. Min Range: -3.5264

Max Act: 3.5264. Min Act: -0.1700

Data Index: 7476684 (Open Web Text)

Max Activating Token Index: 945

Text #1

Max Range: 3.5264. Min Range: -3.5264

Max Act: 3.4749. Min Act: -0.1700

Data Index: 1797300 (Open Web Text)

Max Activating Token Index: 838

Text #2

Max Range: 3.5264. Min Range: -3.5264

Max Act: 3.4653. Min Act: -0.1700

Data Index: 6130820 (Open Web Text)

Max Activating Token Index: 231

Text #3

Max Range: 3.5264. Min Range: -3.5264

Max Act: 3.4444. Min Act: -0.1700

Data Index: 6635013 (Open Web Text)

Max Activating Token Index: 446

Text #4

Max Range: 3.5264. Min Range: -3.5264

Max Act: 3.4264. Min Act: -0.1700

Data Index: 3301983 (Open Web Text)

Max Activating Token Index: 414

Text #5

Max Range: 3.5264. Min Range: -3.5264

Max Act: 3.4251. Min Act: -0.1700

Data Index: 3697210 (Open Web Text)

Max Activating Token Index: 113

Text #6

Max Range: 3.5264. Min Range: -3.5264

Max Act: 3.4324. Min Act: -0.1700

Data Index: 6470443 (Open Web Text)

Max Activating Token Index: 845

Text #7

Max Range: 3.5264. Min Range: -3.5264

Max Act: 3.4288. Min Act: -0.1700

Data Index: 156817 (Open Web Text)

Max Activating Token Index: 740

Text #8

Max Range: 3.5264. Min Range: -3.5264

Max Act: 3.4226. Min Act: -0.1700

Data Index: 3667630 (Open Web Text)

Max Activating Token Index: 123

Text #9

Max Range: 3.5264. Min Range: -3.5264

Max Act: 3.4024. Min Act: -0.1700

Data Index: 1472700 (Open Web Text)

Max Activating Token Index: 358

Text #10

Max Range: 3.5264. Min Range: -3.5264

Max Act: 3.4169. Min Act: -0.1700

Data Index: 3026123 (Open Web Text)

Max Activating Token Index: 1020

Text #11

Max Range: 3.5264. Min Range: -3.5264

Max Act: 3.3992. Min Act: -0.1700

Data Index: 3067438 (Open Web Text)

Max Activating Token Index: 1018

Text #12

Max Range: 3.5264. Min Range: -3.5264

Max Act: 3.4111. Min Act: -0.1700

Data Index: 506383 (Open Web Text)

Max Activating Token Index: 73

Text #13

Max Range: 3.5264. Min Range: -3.5264

Max Act: 3.3727. Min Act: -0.1700

Data Index: 4178910 (Open Web Text)

Max Activating Token Index: 201

Text #14

Max Range: 3.5264. Min Range: -3.5264

Max Act: 3.3815. Min Act: -0.1700

Data Index: 7853252 (Open Web Text)

Max Activating Token Index: 310

Text #15

Max Range: 3.5264. Min Range: -3.5264

Max Act: 3.3758. Min Act: -0.1700

Data Index: 3041867 (Open Web Text)

Max Activating Token Index: 450

Text #16

Max Range: 3.5264. Min Range: -3.5264

Max Act: 3.3703. Min Act: -0.1700

Data Index: 6387097 (Open Web Text)

Max Activating Token Index: 936

Text #17

Max Range: 3.5264. Min Range: -3.5264

Max Act: 3.3985. Min Act: -0.1700

Data Index: 3969070 (Open Web Text)

Max Activating Token Index: 531

Text #18

Max Range: 3.5264. Min Range: -3.5264

Max Act: 3.3940. Min Act: -0.1700

Data Index: 1876840 (Open Web Text)

Max Activating Token Index: 445

Text #19

Max Range: 3.5264. Min Range: -3.5264

Max Act: 3.3679. Min Act: -0.1700

Data Index: 7025616 (Open Web Text)

Max Activating Token Index: 573