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

Dataset: Open Web Text

Neuron 520 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: 4.3490. Min Range: -4.3490

Max Act: 4.3490. Min Act: -0.1700

Data Index: 2590680 (Open Web Text)

Max Activating Token Index: 429

Text #1

Max Range: 4.3490. Min Range: -4.3490

Max Act: 4.1923. Min Act: -0.1700

Data Index: 1617113 (Open Web Text)

Max Activating Token Index: 784

Text #2

Max Range: 4.3490. Min Range: -4.3490

Max Act: 4.0585. Min Act: -0.1700

Data Index: 2892271 (Open Web Text)

Max Activating Token Index: 740

Text #3

Max Range: 4.3490. Min Range: -4.3490

Max Act: 4.0134. Min Act: -0.1700

Data Index: 3887643 (Open Web Text)

Max Activating Token Index: 20

Text #4

Max Range: 4.3490. Min Range: -4.3490

Max Act: 4.0372. Min Act: -0.1700

Data Index: 2156347 (Open Web Text)

Max Activating Token Index: 31

Text #5

Max Range: 4.3490. Min Range: -4.3490

Max Act: 3.9901. Min Act: -0.1700

Data Index: 4351930 (Open Web Text)

Max Activating Token Index: 110

Text #6

Max Range: 4.3490. Min Range: -4.3490

Max Act: 3.9896. Min Act: -0.1700

Data Index: 3607401 (Open Web Text)

Max Activating Token Index: 14

Text #7

Max Range: 4.3490. Min Range: -4.3490

Max Act: 3.9349. Min Act: -0.1700

Data Index: 7471170 (Open Web Text)

Max Activating Token Index: 477

Text #8

Max Range: 4.3490. Min Range: -4.3490

Max Act: 3.9494. Min Act: -0.1700

Data Index: 5009815 (Open Web Text)

Max Activating Token Index: 964

Text #9

Max Range: 4.3490. Min Range: -4.3490

Max Act: 3.9689. Min Act: -0.1700

Data Index: 8446436 (Open Web Text)

Max Activating Token Index: 691

Text #10

Max Range: 4.3490. Min Range: -4.3490

Max Act: 3.9728. Min Act: -0.1700

Data Index: 2121566 (Open Web Text)

Max Activating Token Index: 181

Text #11

Max Range: 4.3490. Min Range: -4.3490

Max Act: 3.9429. Min Act: -0.1700

Data Index: 1808566 (Open Web Text)

Max Activating Token Index: 427

Text #12

Max Range: 4.3490. Min Range: -4.3490

Max Act: 3.9824. Min Act: -0.1700

Data Index: 5130303 (Open Web Text)

Max Activating Token Index: 746

Text #13

Max Range: 4.3490. Min Range: -4.3490

Max Act: 3.9584. Min Act: -0.1700

Data Index: 5842090 (Open Web Text)

Max Activating Token Index: 630

Text #14

Max Range: 4.3490. Min Range: -4.3490

Max Act: 3.9218. Min Act: -0.1700

Data Index: 7389050 (Open Web Text)

Max Activating Token Index: 369

Text #15

Max Range: 4.3490. Min Range: -4.3490

Max Act: 3.9157. Min Act: -0.1700

Data Index: 6728543 (Open Web Text)

Max Activating Token Index: 942

Text #16

Max Range: 4.3490. Min Range: -4.3490

Max Act: 3.9230. Min Act: -0.1700

Data Index: 5618175 (Open Web Text)

Max Activating Token Index: 453

Text #17

Max Range: 4.3490. Min Range: -4.3490

Max Act: 3.9353. Min Act: -0.1700

Data Index: 3146745 (Open Web Text)

Max Activating Token Index: 554

Text #18

Max Range: 4.3490. Min Range: -4.3490

Max Act: 3.8996. Min Act: -0.1700

Data Index: 1890092 (Open Web Text)

Max Activating Token Index: 709

Text #19

Max Range: 4.3490. Min Range: -4.3490

Max Act: 3.9185. Min Act: -0.1700

Data Index: 539057 (Open Web Text)

Max Activating Token Index: 1005