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

Dataset: Open Web Text

Neuron 329 in Layer 1

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: 3.1123. Min Range: -3.1123

Max Act: 3.1123. Min Act: -0.1700

Data Index: 6989511 (Open Web Text)

Max Activating Token Index: 491

Text #1

Max Range: 3.1123. Min Range: -3.1123

Max Act: 3.0520. Min Act: -0.1700

Data Index: 2041569 (Open Web Text)

Max Activating Token Index: 968

Text #2

Max Range: 3.1123. Min Range: -3.1123

Max Act: 3.0150. Min Act: -0.1700

Data Index: 7517738 (Open Web Text)

Max Activating Token Index: 817

Text #3

Max Range: 3.1123. Min Range: -3.1123

Max Act: 3.0169. Min Act: -0.1700

Data Index: 5642557 (Open Web Text)

Max Activating Token Index: 1017

Text #4

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.9964. Min Act: -0.1700

Data Index: 3306696 (Open Web Text)

Max Activating Token Index: 15

Text #5

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.9233. Min Act: -0.1700

Data Index: 7209773 (Open Web Text)

Max Activating Token Index: 615

Text #6

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.9252. Min Act: -0.1700

Data Index: 2477989 (Open Web Text)

Max Activating Token Index: 145

Text #7

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.9065. Min Act: -0.1700

Data Index: 6419730 (Open Web Text)

Max Activating Token Index: 161

Text #8

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.9011. Min Act: -0.1700

Data Index: 2328364 (Open Web Text)

Max Activating Token Index: 567

Text #9

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.8933. Min Act: -0.1700

Data Index: 21395 (Open Web Text)

Max Activating Token Index: 251

Text #10

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.8900. Min Act: -0.1700

Data Index: 4717154 (Open Web Text)

Max Activating Token Index: 860

Text #11

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.9104. Min Act: -0.1700

Data Index: 4473899 (Open Web Text)

Max Activating Token Index: 979

Text #12

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.8679. Min Act: -0.1700

Data Index: 4549194 (Open Web Text)

Max Activating Token Index: 225

Text #13

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.8946. Min Act: -0.1700

Data Index: 6992766 (Open Web Text)

Max Activating Token Index: 974

Text #14

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.8945. Min Act: -0.1700

Data Index: 2065262 (Open Web Text)

Max Activating Token Index: 410

Text #15

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.8742. Min Act: -0.1700

Data Index: 7444629 (Open Web Text)

Max Activating Token Index: 606

Text #16

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.8352. Min Act: -0.1700

Data Index: 747744 (Open Web Text)

Max Activating Token Index: 802

Text #17

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.8484. Min Act: -0.1700

Data Index: 8116648 (Open Web Text)

Max Activating Token Index: 878

Text #18

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.8459. Min Act: -0.1700

Data Index: 7338470 (Open Web Text)

Max Activating Token Index: 698

Text #19

Max Range: 3.1123. Min Range: -3.1123

Max Act: 2.8371. Min Act: -0.1700

Data Index: 5852394 (Open Web Text)

Max Activating Token Index: 790