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

Dataset: Open Web Text

Neuron 1470 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: 6.9789. Min Range: -6.9789

Max Act: 6.9789. Min Act: -0.1700

Data Index: 166588 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 6.9789. Min Range: -6.9789

Max Act: 6.9635. Min Act: -0.1700

Data Index: 1487118 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 6.9789. Min Range: -6.9789

Max Act: 6.9553. Min Act: -0.1700

Data Index: 5038284 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 6.9789. Min Range: -6.9789

Max Act: 6.9214. Min Act: -0.1700

Data Index: 4261596 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 6.9789. Min Range: -6.9789

Max Act: 6.9253. Min Act: -0.1700

Data Index: 7091049 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 6.9789. Min Range: -6.9789

Max Act: 6.9462. Min Act: -0.1700

Data Index: 940503 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 6.9789. Min Range: -6.9789

Max Act: 6.9253. Min Act: -0.1700

Data Index: 4845697 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 6.9789. Min Range: -6.9789

Max Act: 6.9213. Min Act: -0.1700

Data Index: 4368662 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 6.9789. Min Range: -6.9789

Max Act: 6.9123. Min Act: -0.1700

Data Index: 2788137 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 6.9789. Min Range: -6.9789

Max Act: 6.9005. Min Act: -0.1700

Data Index: 4922757 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 6.9789. Min Range: -6.9789

Max Act: 6.9063. Min Act: -0.1700

Data Index: 3274749 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 6.9789. Min Range: -6.9789

Max Act: 6.9274. Min Act: -0.1700

Data Index: 6057974 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 6.9789. Min Range: -6.9789

Max Act: 6.9231. Min Act: -0.1700

Data Index: 2781063 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 6.9789. Min Range: -6.9789

Max Act: 6.9135. Min Act: -0.1700

Data Index: 7291962 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 6.9789. Min Range: -6.9789

Max Act: 6.9041. Min Act: -0.1700

Data Index: 1997668 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 6.9789. Min Range: -6.9789

Max Act: 6.8987. Min Act: -0.1700

Data Index: 1114839 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 6.9789. Min Range: -6.9789

Max Act: 6.9041. Min Act: -0.1700

Data Index: 7380070 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 6.9789. Min Range: -6.9789

Max Act: 6.9005. Min Act: -0.1700

Data Index: 8460564 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 6.9789. Min Range: -6.9789

Max Act: 6.9041. Min Act: -0.1700

Data Index: 1740703 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 6.9789. Min Range: -6.9789

Max Act: 6.8713. Min Act: -0.1700

Data Index: 78776 (Open Web Text)

Max Activating Token Index: 4