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

Dataset: Open Web Text

Neuron 599 in Layer 4

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: 3.8188. Min Range: -3.8188

Max Act: 3.8188. Min Act: -0.1700

Data Index: 8624514 (Open Web Text)

Max Activating Token Index: 290

Text #1

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.6471. Min Act: -0.1700

Data Index: 4034069 (Open Web Text)

Max Activating Token Index: 444

Text #2

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.5219. Min Act: -0.1700

Data Index: 5514260 (Open Web Text)

Max Activating Token Index: 651

Text #3

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.5290. Min Act: -0.1700

Data Index: 3521460 (Open Web Text)

Max Activating Token Index: 910

Text #4

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.5098. Min Act: -0.1700

Data Index: 1900240 (Open Web Text)

Max Activating Token Index: 34

Text #5

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.5199. Min Act: -0.1700

Data Index: 708514 (Open Web Text)

Max Activating Token Index: 1013

Text #6

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.4884. Min Act: -0.1700

Data Index: 3221636 (Open Web Text)

Max Activating Token Index: 229

Text #7

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.4565. Min Act: -0.1700

Data Index: 6415483 (Open Web Text)

Max Activating Token Index: 291

Text #8

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.5004. Min Act: -0.1700

Data Index: 1509708 (Open Web Text)

Max Activating Token Index: 461

Text #9

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.4837. Min Act: -0.1700

Data Index: 4332811 (Open Web Text)

Max Activating Token Index: 860

Text #10

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.4432. Min Act: -0.1700

Data Index: 4685665 (Open Web Text)

Max Activating Token Index: 627

Text #11

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.4413. Min Act: -0.1700

Data Index: 4965190 (Open Web Text)

Max Activating Token Index: 101

Text #12

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.4538. Min Act: -0.1700

Data Index: 4043384 (Open Web Text)

Max Activating Token Index: 125

Text #13

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.4657. Min Act: -0.1700

Data Index: 1675861 (Open Web Text)

Max Activating Token Index: 623

Text #14

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.4504. Min Act: -0.1700

Data Index: 5726919 (Open Web Text)

Max Activating Token Index: 172

Text #15

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.4382. Min Act: -0.1700

Data Index: 4404272 (Open Web Text)

Max Activating Token Index: 929

Text #16

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.4379. Min Act: -0.1700

Data Index: 8735870 (Open Web Text)

Max Activating Token Index: 659

Text #17

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.4317. Min Act: -0.1700

Data Index: 1387452 (Open Web Text)

Max Activating Token Index: 757

Text #18

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.4134. Min Act: -0.1700

Data Index: 6310263 (Open Web Text)

Max Activating Token Index: 696

Text #19

Max Range: 3.8188. Min Range: -3.8188

Max Act: 3.4246. Min Act: -0.1700

Data Index: 7778519 (Open Web Text)

Max Activating Token Index: 857