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

Dataset: Open Web Text

Neuron 1943 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: 4.0579. Min Range: -4.0579

Max Act: 4.0579. Min Act: -0.1700

Data Index: 8187234 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.0579. Min Range: -4.0579

Max Act: 4.0526. Min Act: -0.1700

Data Index: 2397423 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 4.0579. Min Range: -4.0579

Max Act: 4.0269. Min Act: -0.1700

Data Index: 4451577 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.0579. Min Range: -4.0579

Max Act: 4.0354. Min Act: -0.1700

Data Index: 2007179 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.0579. Min Range: -4.0579

Max Act: 4.0107. Min Act: -0.1700

Data Index: 8007253 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.0579. Min Range: -4.0579

Max Act: 4.0107. Min Act: -0.1700

Data Index: 4909795 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 4.0579. Min Range: -4.0579

Max Act: 4.0167. Min Act: -0.1700

Data Index: 2063359 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.0579. Min Range: -4.0579

Max Act: 4.0121. Min Act: -0.1700

Data Index: 7321316 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.0579. Min Range: -4.0579

Max Act: 3.9805. Min Act: -0.1700

Data Index: 3182400 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.0579. Min Range: -4.0579

Max Act: 3.9785. Min Act: -0.1700

Data Index: 278722 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 4.0579. Min Range: -4.0579

Max Act: 3.9866. Min Act: -0.1700

Data Index: 7812426 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 4.0579. Min Range: -4.0579

Max Act: 3.9775. Min Act: -0.1700

Data Index: 3982278 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.0579. Min Range: -4.0579

Max Act: 3.9348. Min Act: -0.1700

Data Index: 1732128 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.0579. Min Range: -4.0579

Max Act: 3.9482. Min Act: -0.1700

Data Index: 5356110 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.0579. Min Range: -4.0579

Max Act: 3.9308. Min Act: -0.1700

Data Index: 7938669 (Open Web Text)

Max Activating Token Index: 11

Text #15

Max Range: 4.0579. Min Range: -4.0579

Max Act: 3.9558. Min Act: -0.1700

Data Index: 5035728 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 4.0579. Min Range: -4.0579

Max Act: 3.9462. Min Act: -0.1700

Data Index: 4059350 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.0579. Min Range: -4.0579

Max Act: 3.9088. Min Act: -0.1700

Data Index: 1742180 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 4.0579. Min Range: -4.0579

Max Act: 3.9093. Min Act: -0.1700

Data Index: 58067 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 4.0579. Min Range: -4.0579

Max Act: 3.9088. Min Act: -0.1700

Data Index: 109911 (Open Web Text)

Max Activating Token Index: 2