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

Dataset: Open Web Text

Neuron 3059 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: 3.3029. Min Range: -3.3029

Max Act: 3.3029. Min Act: -0.1700

Data Index: 4200380 (Open Web Text)

Max Activating Token Index: 322

Text #1

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.1701. Min Act: -0.1700

Data Index: 425995 (Open Web Text)

Max Activating Token Index: 379

Text #2

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.1517. Min Act: -0.1700

Data Index: 894617 (Open Web Text)

Max Activating Token Index: 464

Text #3

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.1236. Min Act: -0.1700

Data Index: 8545386 (Open Web Text)

Max Activating Token Index: 80

Text #4

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.1205. Min Act: -0.1700

Data Index: 5706668 (Open Web Text)

Max Activating Token Index: 675

Text #5

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.1034. Min Act: -0.1700

Data Index: 4610027 (Open Web Text)

Max Activating Token Index: 408

Text #6

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.0780. Min Act: -0.1700

Data Index: 4681216 (Open Web Text)

Max Activating Token Index: 922

Text #7

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.0677. Min Act: -0.1700

Data Index: 3874882 (Open Web Text)

Max Activating Token Index: 756

Text #8

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.0603. Min Act: -0.1700

Data Index: 5603901 (Open Web Text)

Max Activating Token Index: 206

Text #9

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.0569. Min Act: -0.1700

Data Index: 5412429 (Open Web Text)

Max Activating Token Index: 240

Text #10

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.0417. Min Act: -0.1700

Data Index: 818413 (Open Web Text)

Max Activating Token Index: 487

Text #11

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.0404. Min Act: -0.1700

Data Index: 6057507 (Open Web Text)

Max Activating Token Index: 397

Text #12

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.0522. Min Act: -0.1700

Data Index: 1621628 (Open Web Text)

Max Activating Token Index: 681

Text #13

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.0400. Min Act: -0.1700

Data Index: 1039971 (Open Web Text)

Max Activating Token Index: 741

Text #14

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.0392. Min Act: -0.1700

Data Index: 6751982 (Open Web Text)

Max Activating Token Index: 376

Text #15

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.0458. Min Act: -0.1700

Data Index: 8180038 (Open Web Text)

Max Activating Token Index: 393

Text #16

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.0501. Min Act: -0.1700

Data Index: 797453 (Open Web Text)

Max Activating Token Index: 411

Text #17

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.0457. Min Act: -0.1700

Data Index: 6261690 (Open Web Text)

Max Activating Token Index: 260

Text #18

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.0400. Min Act: -0.1700

Data Index: 2558152 (Open Web Text)

Max Activating Token Index: 185

Text #19

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.0410. Min Act: -0.1700

Data Index: 3252329 (Open Web Text)

Max Activating Token Index: 751