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

Dataset: Open Web Text

Neuron 456 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: 1.9503. Min Range: -1.9503

Max Act: 1.9503. Min Act: -0.1700

Data Index: 295092 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.9503. Min Range: -1.9503

Max Act: 1.9210. Min Act: -0.1700

Data Index: 6710997 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 1.9503. Min Range: -1.9503

Max Act: 1.9023. Min Act: -0.1700

Data Index: 3140283 (Open Web Text)

Max Activating Token Index: 720

Text #3

Max Range: 1.9503. Min Range: -1.9503

Max Act: 1.8959. Min Act: -0.1700

Data Index: 8616179 (Open Web Text)

Max Activating Token Index: 971

Text #4

Max Range: 1.9503. Min Range: -1.9503

Max Act: 1.8895. Min Act: -0.1700

Data Index: 7472384 (Open Web Text)

Max Activating Token Index: 721

Text #5

Max Range: 1.9503. Min Range: -1.9503

Max Act: 1.9151. Min Act: -0.1700

Data Index: 819476 (Open Web Text)

Max Activating Token Index: 16

Text #6

Max Range: 1.9503. Min Range: -1.9503

Max Act: 1.9109. Min Act: -0.1700

Data Index: 471515 (Open Web Text)

Max Activating Token Index: 531

Text #7

Max Range: 1.9503. Min Range: -1.9503

Max Act: 1.8913. Min Act: -0.1700

Data Index: 2416270 (Open Web Text)

Max Activating Token Index: 717

Text #8

Max Range: 1.9503. Min Range: -1.9503

Max Act: 1.8803. Min Act: -0.1700

Data Index: 3156975 (Open Web Text)

Max Activating Token Index: 369

Text #9

Max Range: 1.9503. Min Range: -1.9503

Max Act: 1.8777. Min Act: -0.1700

Data Index: 6393391 (Open Web Text)

Max Activating Token Index: 341

Text #10

Max Range: 1.9503. Min Range: -1.9503

Max Act: 1.8865. Min Act: -0.1700

Data Index: 5611877 (Open Web Text)

Max Activating Token Index: 540

Text #11

Max Range: 1.9503. Min Range: -1.9503

Max Act: 1.8561. Min Act: -0.1700

Data Index: 6877794 (Open Web Text)

Max Activating Token Index: 731

Text #12

Max Range: 1.9503. Min Range: -1.9503

Max Act: 1.8798. Min Act: -0.1700

Data Index: 2896744 (Open Web Text)

Max Activating Token Index: 30

Text #13

Max Range: 1.9503. Min Range: -1.9503

Max Act: 1.8713. Min Act: -0.1700

Data Index: 5001457 (Open Web Text)

Max Activating Token Index: 491

Text #14

Max Range: 1.9503. Min Range: -1.9503

Max Act: 1.8514. Min Act: -0.1700

Data Index: 7379464 (Open Web Text)

Max Activating Token Index: 709

Text #15

Max Range: 1.9503. Min Range: -1.9503

Max Act: 1.8794. Min Act: -0.1700

Data Index: 2760403 (Open Web Text)

Max Activating Token Index: 12

Text #16

Max Range: 1.9503. Min Range: -1.9503

Max Act: 1.8455. Min Act: -0.1700

Data Index: 8191075 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 1.9503. Min Range: -1.9503

Max Act: 1.8805. Min Act: -0.1700

Data Index: 4336189 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 1.9503. Min Range: -1.9503

Max Act: 1.8726. Min Act: -0.1700

Data Index: 3407138 (Open Web Text)

Max Activating Token Index: 41

Text #19

Max Range: 1.9503. Min Range: -1.9503

Max Act: 1.8666. Min Act: -0.1700

Data Index: 4263904 (Open Web Text)

Max Activating Token Index: 1023