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

Dataset: Open Web Text

Neuron 1079 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: 3.0948. Min Range: -3.0948

Max Act: 3.0948. Min Act: -0.1700

Data Index: 2419860 (Open Web Text)

Max Activating Token Index: 883

Text #1

Max Range: 3.0948. Min Range: -3.0948

Max Act: 3.0558. Min Act: -0.1700

Data Index: 3578507 (Open Web Text)

Max Activating Token Index: 535

Text #2

Max Range: 3.0948. Min Range: -3.0948

Max Act: 3.0314. Min Act: -0.1700

Data Index: 6928220 (Open Web Text)

Max Activating Token Index: 781

Text #3

Max Range: 3.0948. Min Range: -3.0948

Max Act: 3.0394. Min Act: -0.1700

Data Index: 3769335 (Open Web Text)

Max Activating Token Index: 741

Text #4

Max Range: 3.0948. Min Range: -3.0948

Max Act: 3.0041. Min Act: -0.1700

Data Index: 5686793 (Open Web Text)

Max Activating Token Index: 114

Text #5

Max Range: 3.0948. Min Range: -3.0948

Max Act: 2.9925. Min Act: -0.1700

Data Index: 2089515 (Open Web Text)

Max Activating Token Index: 253

Text #6

Max Range: 3.0948. Min Range: -3.0948

Max Act: 2.9786. Min Act: -0.1700

Data Index: 3366731 (Open Web Text)

Max Activating Token Index: 112

Text #7

Max Range: 3.0948. Min Range: -3.0948

Max Act: 2.9534. Min Act: -0.1700

Data Index: 208071 (Open Web Text)

Max Activating Token Index: 713

Text #8

Max Range: 3.0948. Min Range: -3.0948

Max Act: 2.9304. Min Act: -0.1700

Data Index: 5340582 (Open Web Text)

Max Activating Token Index: 125

Text #9

Max Range: 3.0948. Min Range: -3.0948

Max Act: 2.9323. Min Act: -0.1700

Data Index: 7349197 (Open Web Text)

Max Activating Token Index: 277

Text #10

Max Range: 3.0948. Min Range: -3.0948

Max Act: 2.8962. Min Act: -0.1700

Data Index: 4555945 (Open Web Text)

Max Activating Token Index: 842

Text #11

Max Range: 3.0948. Min Range: -3.0948

Max Act: 2.9220. Min Act: -0.1700

Data Index: 230404 (Open Web Text)

Max Activating Token Index: 869

Text #12

Max Range: 3.0948. Min Range: -3.0948

Max Act: 2.9031. Min Act: -0.1700

Data Index: 7679076 (Open Web Text)

Max Activating Token Index: 218

Text #13

Max Range: 3.0948. Min Range: -3.0948

Max Act: 2.9035. Min Act: -0.1700

Data Index: 646844 (Open Web Text)

Max Activating Token Index: 855

Text #14

Max Range: 3.0948. Min Range: -3.0948

Max Act: 2.8843. Min Act: -0.1700

Data Index: 4698655 (Open Web Text)

Max Activating Token Index: 261

Text #15

Max Range: 3.0948. Min Range: -3.0948

Max Act: 2.8889. Min Act: -0.1700

Data Index: 5158190 (Open Web Text)

Max Activating Token Index: 523

Text #16

Max Range: 3.0948. Min Range: -3.0948

Max Act: 2.8757. Min Act: -0.1700

Data Index: 3825040 (Open Web Text)

Max Activating Token Index: 668

Text #17

Max Range: 3.0948. Min Range: -3.0948

Max Act: 2.8671. Min Act: -0.1700

Data Index: 2252184 (Open Web Text)

Max Activating Token Index: 991

Text #18

Max Range: 3.0948. Min Range: -3.0948

Max Act: 2.8895. Min Act: -0.1700

Data Index: 6425057 (Open Web Text)

Max Activating Token Index: 33

Text #19

Max Range: 3.0948. Min Range: -3.0948

Max Act: 2.8846. Min Act: -0.1700

Data Index: 3772342 (Open Web Text)

Max Activating Token Index: 614