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

Dataset: Open Web Text

Neuron 3070 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: 3.2677. Min Range: -3.2677

Max Act: 3.2604. Min Act: -0.1700

Data Index: 2646866 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.2677. Min Range: -3.2677

Max Act: 3.2677. Min Act: -0.1700

Data Index: 3821493 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.2677. Min Range: -3.2677

Max Act: 3.2611. Min Act: -0.1700

Data Index: 5395634 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.2677. Min Range: -3.2677

Max Act: 3.2665. Min Act: -0.1700

Data Index: 5177220 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.2677. Min Range: -3.2677

Max Act: 3.2665. Min Act: -0.1700

Data Index: 119921 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.2677. Min Range: -3.2677

Max Act: 3.2523. Min Act: -0.1700

Data Index: 6912323 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.2677. Min Range: -3.2677

Max Act: 3.2380. Min Act: -0.1700

Data Index: 6088795 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.2677. Min Range: -3.2677

Max Act: 3.2493. Min Act: -0.1700

Data Index: 2361792 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.2677. Min Range: -3.2677

Max Act: 3.2380. Min Act: -0.1700

Data Index: 7509643 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 3.2677. Min Range: -3.2677

Max Act: 3.2380. Min Act: -0.1700

Data Index: 8732579 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 3.2677. Min Range: -3.2677

Max Act: 3.2281. Min Act: -0.1700

Data Index: 7091764 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.2677. Min Range: -3.2677

Max Act: 3.2281. Min Act: -0.1700

Data Index: 3190910 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.2677. Min Range: -3.2677

Max Act: 3.2335. Min Act: -0.1700

Data Index: 4402101 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.2677. Min Range: -3.2677

Max Act: 3.2365. Min Act: -0.1700

Data Index: 2976021 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.2677. Min Range: -3.2677

Max Act: 3.2365. Min Act: -0.1700

Data Index: 3776045 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.2677. Min Range: -3.2677

Max Act: 3.2164. Min Act: -0.1700

Data Index: 1762884 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.2677. Min Range: -3.2677

Max Act: 3.2205. Min Act: -0.1700

Data Index: 1050710 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.2677. Min Range: -3.2677

Max Act: 3.2101. Min Act: -0.1700

Data Index: 3041038 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 3.2677. Min Range: -3.2677

Max Act: 3.2164. Min Act: -0.1700

Data Index: 3529292 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 3.2677. Min Range: -3.2677

Max Act: 3.2237. Min Act: -0.1700

Data Index: 3661513 (Open Web Text)

Max Activating Token Index: 3