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

Dataset: Open Web Text

Neuron 2793 in Layer 6

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: 3.1725. Min Range: -3.1725

Max Act: 3.1725. Min Act: -0.1700

Data Index: 7834598 (Open Web Text)

Max Activating Token Index: 46

Text #1

Max Range: 3.1725. Min Range: -3.1725

Max Act: 3.0701. Min Act: -0.1700

Data Index: 6791319 (Open Web Text)

Max Activating Token Index: 939

Text #2

Max Range: 3.1725. Min Range: -3.1725

Max Act: 3.0477. Min Act: -0.1700

Data Index: 2496771 (Open Web Text)

Max Activating Token Index: 427

Text #3

Max Range: 3.1725. Min Range: -3.1725

Max Act: 3.0384. Min Act: -0.1700

Data Index: 8463984 (Open Web Text)

Max Activating Token Index: 584

Text #4

Max Range: 3.1725. Min Range: -3.1725

Max Act: 3.0079. Min Act: -0.1700

Data Index: 5339170 (Open Web Text)

Max Activating Token Index: 720

Text #5

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.9655. Min Act: -0.1700

Data Index: 7164371 (Open Web Text)

Max Activating Token Index: 878

Text #6

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.9573. Min Act: -0.1700

Data Index: 1442853 (Open Web Text)

Max Activating Token Index: 742

Text #7

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.9393. Min Act: -0.1700

Data Index: 964319 (Open Web Text)

Max Activating Token Index: 672

Text #8

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.9565. Min Act: -0.1700

Data Index: 3918853 (Open Web Text)

Max Activating Token Index: 193

Text #9

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.9307. Min Act: -0.1700

Data Index: 8158782 (Open Web Text)

Max Activating Token Index: 273

Text #10

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.9466. Min Act: -0.1700

Data Index: 7077085 (Open Web Text)

Max Activating Token Index: 698

Text #11

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.9131. Min Act: -0.1700

Data Index: 6905708 (Open Web Text)

Max Activating Token Index: 706

Text #12

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.9330. Min Act: -0.1700

Data Index: 4598432 (Open Web Text)

Max Activating Token Index: 436

Text #13

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.9052. Min Act: -0.1700

Data Index: 5542023 (Open Web Text)

Max Activating Token Index: 110

Text #14

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.9205. Min Act: -0.1700

Data Index: 4830878 (Open Web Text)

Max Activating Token Index: 402

Text #15

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.9087. Min Act: -0.1700

Data Index: 3810314 (Open Web Text)

Max Activating Token Index: 476

Text #16

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.9170. Min Act: -0.1700

Data Index: 5937746 (Open Web Text)

Max Activating Token Index: 373

Text #17

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.8901. Min Act: -0.1700

Data Index: 6581930 (Open Web Text)

Max Activating Token Index: 380

Text #18

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.8959. Min Act: -0.1700

Data Index: 6535502 (Open Web Text)

Max Activating Token Index: 594

Text #19

Max Range: 3.1725. Min Range: -3.1725

Max Act: 2.8998. Min Act: -0.1700

Data Index: 2936079 (Open Web Text)

Max Activating Token Index: 347