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

Dataset: Open Web Text

Neuron 1809 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: 2.0034. Min Range: -2.0034

Max Act: 2.0034. Min Act: -0.1700

Data Index: 2439889 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 2.0034. Min Range: -2.0034

Max Act: 2.0015. Min Act: -0.1700

Data Index: 1417430 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 2.0034. Min Range: -2.0034

Max Act: 1.9819. Min Act: -0.1700

Data Index: 70447 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 2.0034. Min Range: -2.0034

Max Act: 1.9885. Min Act: -0.1700

Data Index: 3072208 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 2.0034. Min Range: -2.0034

Max Act: 1.9669. Min Act: -0.1700

Data Index: 6829613 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 2.0034. Min Range: -2.0034

Max Act: 1.9611. Min Act: -0.1700

Data Index: 5003501 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 2.0034. Min Range: -2.0034

Max Act: 1.9590. Min Act: -0.1700

Data Index: 3372003 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 2.0034. Min Range: -2.0034

Max Act: 1.9406. Min Act: -0.1700

Data Index: 2824918 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 2.0034. Min Range: -2.0034

Max Act: 1.9358. Min Act: -0.1700

Data Index: 460127 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 2.0034. Min Range: -2.0034

Max Act: 1.9306. Min Act: -0.1700

Data Index: 4494423 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 2.0034. Min Range: -2.0034

Max Act: 1.9230. Min Act: -0.1700

Data Index: 880854 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 2.0034. Min Range: -2.0034

Max Act: 1.9209. Min Act: -0.1700

Data Index: 2629934 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 2.0034. Min Range: -2.0034

Max Act: 1.9055. Min Act: -0.1700

Data Index: 4491564 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 2.0034. Min Range: -2.0034

Max Act: 1.9037. Min Act: -0.1700

Data Index: 5339713 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 2.0034. Min Range: -2.0034

Max Act: 1.9114. Min Act: -0.1700

Data Index: 3467392 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 2.0034. Min Range: -2.0034

Max Act: 1.8964. Min Act: -0.1699

Data Index: 242501 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 2.0034. Min Range: -2.0034

Max Act: 1.9038. Min Act: -0.1700

Data Index: 7244323 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 2.0034. Min Range: -2.0034

Max Act: 1.9039. Min Act: -0.1700

Data Index: 6699079 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 2.0034. Min Range: -2.0034

Max Act: 1.8835. Min Act: -0.1700

Data Index: 6261963 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 2.0034. Min Range: -2.0034

Max Act: 1.8992. Min Act: -0.1700

Data Index: 7011235 (Open Web Text)

Max Activating Token Index: 1023