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

Dataset: Open Web Text

Neuron 1977 in Layer 5

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: 2.2223. Min Range: -2.2223

Max Act: 2.2223. Min Act: -0.1700

Data Index: 8658981 (Open Web Text)

Max Activating Token Index: 661

Text #1

Max Range: 2.2223. Min Range: -2.2223

Max Act: 2.1969. Min Act: -0.1700

Data Index: 3731065 (Open Web Text)

Max Activating Token Index: 449

Text #2

Max Range: 2.2223. Min Range: -2.2223

Max Act: 2.2040. Min Act: -0.1700

Data Index: 4129445 (Open Web Text)

Max Activating Token Index: 811

Text #3

Max Range: 2.2223. Min Range: -2.2223

Max Act: 2.1840. Min Act: -0.1700

Data Index: 5032861 (Open Web Text)

Max Activating Token Index: 272

Text #4

Max Range: 2.2223. Min Range: -2.2223

Max Act: 2.1952. Min Act: -0.1700

Data Index: 78606 (Open Web Text)

Max Activating Token Index: 72

Text #5

Max Range: 2.2223. Min Range: -2.2223

Max Act: 2.1696. Min Act: -0.1700

Data Index: 2614961 (Open Web Text)

Max Activating Token Index: 730

Text #6

Max Range: 2.2223. Min Range: -2.2223

Max Act: 2.1486. Min Act: -0.1700

Data Index: 186769 (Open Web Text)

Max Activating Token Index: 227

Text #7

Max Range: 2.2223. Min Range: -2.2223

Max Act: 2.1430. Min Act: -0.1700

Data Index: 3784899 (Open Web Text)

Max Activating Token Index: 387

Text #8

Max Range: 2.2223. Min Range: -2.2223

Max Act: 2.1662. Min Act: -0.1700

Data Index: 363571 (Open Web Text)

Max Activating Token Index: 348

Text #9

Max Range: 2.2223. Min Range: -2.2223

Max Act: 2.1749. Min Act: -0.1700

Data Index: 560870 (Open Web Text)

Max Activating Token Index: 388

Text #10

Max Range: 2.2223. Min Range: -2.2223

Max Act: 2.1785. Min Act: -0.1700

Data Index: 2500878 (Open Web Text)

Max Activating Token Index: 990

Text #11

Max Range: 2.2223. Min Range: -2.2223

Max Act: 2.1196. Min Act: -0.1700

Data Index: 7767424 (Open Web Text)

Max Activating Token Index: 707

Text #12

Max Range: 2.2223. Min Range: -2.2223

Max Act: 2.1515. Min Act: -0.1700

Data Index: 4012233 (Open Web Text)

Max Activating Token Index: 874

Text #13

Max Range: 2.2223. Min Range: -2.2223

Max Act: 2.1231. Min Act: -0.1700

Data Index: 7901284 (Open Web Text)

Max Activating Token Index: 580

Text #14

Max Range: 2.2223. Min Range: -2.2223

Max Act: 2.1337. Min Act: -0.1700

Data Index: 7740958 (Open Web Text)

Max Activating Token Index: 578

Text #15

Max Range: 2.2223. Min Range: -2.2223

Max Act: 2.1462. Min Act: -0.1700

Data Index: 5663799 (Open Web Text)

Max Activating Token Index: 985

Text #16

Max Range: 2.2223. Min Range: -2.2223

Max Act: 2.1197. Min Act: -0.1700

Data Index: 4577625 (Open Web Text)

Max Activating Token Index: 78

Text #17

Max Range: 2.2223. Min Range: -2.2223

Max Act: 2.1417. Min Act: -0.1700

Data Index: 5857371 (Open Web Text)

Max Activating Token Index: 801

Text #18

Max Range: 2.2223. Min Range: -2.2223

Max Act: 2.1315. Min Act: -0.1700

Data Index: 5872466 (Open Web Text)

Max Activating Token Index: 577

Text #19

Max Range: 2.2223. Min Range: -2.2223

Max Act: 2.1385. Min Act: -0.1700

Data Index: 6532148 (Open Web Text)

Max Activating Token Index: 715