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

Dataset: Open Web Text

Neuron 1284 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: 1.3443. Min Range: -1.3443

Max Act: 1.3443. Min Act: -0.1700

Data Index: 7421614 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.3443. Min Range: -1.3443

Max Act: 0.9491. Min Act: -0.1700

Data Index: 7887528 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 1.3443. Min Range: -1.3443

Max Act: 0.8979. Min Act: -0.1700

Data Index: 7164208 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 1.3443. Min Range: -1.3443

Max Act: 0.9017. Min Act: -0.1700

Data Index: 3169646 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.3443. Min Range: -1.3443

Max Act: 0.8855. Min Act: -0.1700

Data Index: 8667742 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 1.3443. Min Range: -1.3443

Max Act: 0.8834. Min Act: -0.1700

Data Index: 241409 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 1.3443. Min Range: -1.3443

Max Act: 0.8789. Min Act: -0.1697

Data Index: 7817928 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 1.3443. Min Range: -1.3443

Max Act: 0.8814. Min Act: -0.1700

Data Index: 7084739 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 1.3443. Min Range: -1.3443

Max Act: 0.8794. Min Act: -0.1700

Data Index: 4847417 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 1.3443. Min Range: -1.3443

Max Act: 0.8672. Min Act: -0.1700

Data Index: 7650724 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 1.3443. Min Range: -1.3443

Max Act: 0.8736. Min Act: -0.1700

Data Index: 8172797 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 1.3443. Min Range: -1.3443

Max Act: 0.8627. Min Act: -0.1700

Data Index: 5831146 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 1.3443. Min Range: -1.3443

Max Act: 0.8666. Min Act: -0.1700

Data Index: 5835860 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 1.3443. Min Range: -1.3443

Max Act: 0.8625. Min Act: -0.1700

Data Index: 1779203 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 1.3443. Min Range: -1.3443

Max Act: 0.8559. Min Act: -0.1700

Data Index: 6158605 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 1.3443. Min Range: -1.3443

Max Act: 0.8513. Min Act: -0.1700

Data Index: 6179463 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 1.3443. Min Range: -1.3443

Max Act: 0.8531. Min Act: -0.1700

Data Index: 7925966 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 1.3443. Min Range: -1.3443

Max Act: 0.8581. Min Act: -0.1700

Data Index: 878678 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 1.3443. Min Range: -1.3443

Max Act: 0.8563. Min Act: -0.1700

Data Index: 290655 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 1.3443. Min Range: -1.3443

Max Act: 0.8447. Min Act: -0.1700

Data Index: 581317 (Open Web Text)

Max Activating Token Index: 1023