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

Dataset: Open Web Text

Neuron 2594 in Layer 2

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: 1.8780. Min Range: -1.8780

Max Act: 1.8780. Min Act: -0.1700

Data Index: 8106253 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 1.8780. Min Range: -1.8780

Max Act: 1.8209. Min Act: -0.1698

Data Index: 5840397 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 1.8780. Min Range: -1.8780

Max Act: 1.8168. Min Act: -0.1700

Data Index: 4003875 (Open Web Text)

Max Activating Token Index: 33

Text #3

Max Range: 1.8780. Min Range: -1.8780

Max Act: 1.7971. Min Act: -0.1700

Data Index: 5595866 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 1.8780. Min Range: -1.8780

Max Act: 1.7858. Min Act: -0.1700

Data Index: 6090523 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 1.8780. Min Range: -1.8780

Max Act: 1.7761. Min Act: -0.1700

Data Index: 864462 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 1.8780. Min Range: -1.8780

Max Act: 1.7753. Min Act: -0.1700

Data Index: 8214259 (Open Web Text)

Max Activating Token Index: 17

Text #7

Max Range: 1.8780. Min Range: -1.8780

Max Act: 1.7797. Min Act: -0.1700

Data Index: 7817158 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 1.8780. Min Range: -1.8780

Max Act: 1.7639. Min Act: -0.1700

Data Index: 3789420 (Open Web Text)

Max Activating Token Index: 10

Text #9

Max Range: 1.8780. Min Range: -1.8780

Max Act: 1.7579. Min Act: -0.1700

Data Index: 2467455 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 1.8780. Min Range: -1.8780

Max Act: 1.7366. Min Act: -0.1700

Data Index: 8175438 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 1.8780. Min Range: -1.8780

Max Act: 1.7407. Min Act: -0.1700

Data Index: 4820287 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 1.8780. Min Range: -1.8780

Max Act: 1.7279. Min Act: -0.1700

Data Index: 5871241 (Open Web Text)

Max Activating Token Index: 71

Text #13

Max Range: 1.8780. Min Range: -1.8780

Max Act: 1.7329. Min Act: -0.1699

Data Index: 5596822 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 1.8780. Min Range: -1.8780

Max Act: 1.7222. Min Act: -0.1700

Data Index: 2443177 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 1.8780. Min Range: -1.8780

Max Act: 1.7107. Min Act: -0.1700

Data Index: 6130566 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 1.8780. Min Range: -1.8780

Max Act: 1.6933. Min Act: -0.1700

Data Index: 2473897 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 1.8780. Min Range: -1.8780

Max Act: 1.7000. Min Act: -0.1697

Data Index: 7671956 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 1.8780. Min Range: -1.8780

Max Act: 1.7000. Min Act: -0.1700

Data Index: 6041076 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 1.8780. Min Range: -1.8780

Max Act: 1.7000. Min Act: -0.1700

Data Index: 4536927 (Open Web Text)

Max Activating Token Index: 3