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

Dataset: Open Web Text

Neuron 2886 in Layer 0

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: 2.4256. Min Range: -2.4256

Max Act: 2.4256. Min Act: -0.1700

Data Index: 5857742 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 2.4256. Min Range: -2.4256

Max Act: 2.3651. Min Act: -0.1700

Data Index: 7470384 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.4256. Min Range: -2.4256

Max Act: 2.3482. Min Act: -0.1700

Data Index: 3750728 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 2.4256. Min Range: -2.4256

Max Act: 2.3548. Min Act: -0.1700

Data Index: 1020866 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 2.4256. Min Range: -2.4256

Max Act: 2.3601. Min Act: -0.1700

Data Index: 5101998 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 2.4256. Min Range: -2.4256

Max Act: 2.3300. Min Act: -0.1700

Data Index: 7983143 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 2.4256. Min Range: -2.4256

Max Act: 2.3385. Min Act: -0.1700

Data Index: 7248667 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 2.4256. Min Range: -2.4256

Max Act: 2.3409. Min Act: -0.1700

Data Index: 7036286 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.4256. Min Range: -2.4256

Max Act: 2.3346. Min Act: -0.1700

Data Index: 4744694 (Open Web Text)

Max Activating Token Index: 29

Text #9

Max Range: 2.4256. Min Range: -2.4256

Max Act: 2.3365. Min Act: -0.1700

Data Index: 5702502 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 2.4256. Min Range: -2.4256

Max Act: 2.3290. Min Act: -0.1700

Data Index: 3847105 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 2.4256. Min Range: -2.4256

Max Act: 2.3448. Min Act: -0.1700

Data Index: 3815636 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.4256. Min Range: -2.4256

Max Act: 2.3139. Min Act: -0.1700

Data Index: 4287322 (Open Web Text)

Max Activating Token Index: 13

Text #13

Max Range: 2.4256. Min Range: -2.4256

Max Act: 2.3132. Min Act: -0.1700

Data Index: 2876827 (Open Web Text)

Max Activating Token Index: 499

Text #14

Max Range: 2.4256. Min Range: -2.4256

Max Act: 2.3120. Min Act: -0.1700

Data Index: 2959727 (Open Web Text)

Max Activating Token Index: 19

Text #15

Max Range: 2.4256. Min Range: -2.4256

Max Act: 2.3273. Min Act: -0.1700

Data Index: 1022221 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 2.4256. Min Range: -2.4256

Max Act: 2.3256. Min Act: -0.1700

Data Index: 5598564 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 2.4256. Min Range: -2.4256

Max Act: 2.3180. Min Act: -0.1700

Data Index: 5490557 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 2.4256. Min Range: -2.4256

Max Act: 2.3102. Min Act: -0.1700

Data Index: 3397957 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 2.4256. Min Range: -2.4256

Max Act: 2.3125. Min Act: -0.1700

Data Index: 1535719 (Open Web Text)

Max Activating Token Index: 933