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

Dataset: Open Web Text

Neuron 1271 in Layer 3

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: 4.0277. Min Range: -4.0277

Max Act: 4.0086. Min Act: -0.1700

Data Index: 464848 (Open Web Text)

Max Activating Token Index: 860

Text #1

Max Range: 4.0277. Min Range: -4.0277

Max Act: 4.0277. Min Act: -0.1700

Data Index: 464845 (Open Web Text)

Max Activating Token Index: 584

Text #2

Max Range: 4.0277. Min Range: -4.0277

Max Act: 3.9823. Min Act: -0.1700

Data Index: 7815095 (Open Web Text)

Max Activating Token Index: 662

Text #3

Max Range: 4.0277. Min Range: -4.0277

Max Act: 3.9147. Min Act: -0.1700

Data Index: 7099165 (Open Web Text)

Max Activating Token Index: 638

Text #4

Max Range: 4.0277. Min Range: -4.0277

Max Act: 3.8616. Min Act: -0.1700

Data Index: 1267789 (Open Web Text)

Max Activating Token Index: 751

Text #5

Max Range: 4.0277. Min Range: -4.0277

Max Act: 3.8291. Min Act: -0.1700

Data Index: 7085409 (Open Web Text)

Max Activating Token Index: 636

Text #6

Max Range: 4.0277. Min Range: -4.0277

Max Act: 3.7566. Min Act: -0.1700

Data Index: 3640915 (Open Web Text)

Max Activating Token Index: 729

Text #7

Max Range: 4.0277. Min Range: -4.0277

Max Act: 3.7660. Min Act: -0.1700

Data Index: 3872957 (Open Web Text)

Max Activating Token Index: 594

Text #8

Max Range: 4.0277. Min Range: -4.0277

Max Act: 3.8016. Min Act: -0.1700

Data Index: 6551566 (Open Web Text)

Max Activating Token Index: 628

Text #9

Max Range: 4.0277. Min Range: -4.0277

Max Act: 3.7590. Min Act: -0.1700

Data Index: 2277138 (Open Web Text)

Max Activating Token Index: 591

Text #10

Max Range: 4.0277. Min Range: -4.0277

Max Act: 3.7789. Min Act: -0.1700

Data Index: 4662041 (Open Web Text)

Max Activating Token Index: 373

Text #11

Max Range: 4.0277. Min Range: -4.0277

Max Act: 3.7595. Min Act: -0.1700

Data Index: 5897762 (Open Web Text)

Max Activating Token Index: 378

Text #12

Max Range: 4.0277. Min Range: -4.0277

Max Act: 3.7709. Min Act: -0.1700

Data Index: 1633261 (Open Web Text)

Max Activating Token Index: 328

Text #13

Max Range: 4.0277. Min Range: -4.0277

Max Act: 3.7410. Min Act: -0.1700

Data Index: 46367 (Open Web Text)

Max Activating Token Index: 325

Text #14

Max Range: 4.0277. Min Range: -4.0277

Max Act: 3.7563. Min Act: -0.1700

Data Index: 8353506 (Open Web Text)

Max Activating Token Index: 218

Text #15

Max Range: 4.0277. Min Range: -4.0277

Max Act: 3.7364. Min Act: -0.1700

Data Index: 6787403 (Open Web Text)

Max Activating Token Index: 458

Text #16

Max Range: 4.0277. Min Range: -4.0277

Max Act: 3.7274. Min Act: -0.1700

Data Index: 6816889 (Open Web Text)

Max Activating Token Index: 953

Text #17

Max Range: 4.0277. Min Range: -4.0277

Max Act: 3.7284. Min Act: -0.1700

Data Index: 4841113 (Open Web Text)

Max Activating Token Index: 132

Text #18

Max Range: 4.0277. Min Range: -4.0277

Max Act: 3.7578. Min Act: -0.1700

Data Index: 8118527 (Open Web Text)

Max Activating Token Index: 516

Text #19

Max Range: 4.0277. Min Range: -4.0277

Max Act: 3.7227. Min Act: -0.1700

Data Index: 17545 (Open Web Text)

Max Activating Token Index: 87