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

Dataset: Open Web Text

Neuron 1106 in Layer 0

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: 3.8863. Min Range: -3.8863

Max Act: 3.8863. Min Act: -0.1700

Data Index: 2535893 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.8863. Min Range: -3.8863

Max Act: 3.7177. Min Act: -0.1700

Data Index: 5574581 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.8863. Min Range: -3.8863

Max Act: 3.7181. Min Act: -0.1700

Data Index: 7619565 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 3.8863. Min Range: -3.8863

Max Act: 3.7076. Min Act: -0.1700

Data Index: 2352988 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.8863. Min Range: -3.8863

Max Act: 3.6790. Min Act: -0.1700

Data Index: 7948030 (Open Web Text)

Max Activating Token Index: 13

Text #5

Max Range: 3.8863. Min Range: -3.8863

Max Act: 3.7047. Min Act: -0.1700

Data Index: 8183918 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.8863. Min Range: -3.8863

Max Act: 3.6566. Min Act: -0.1700

Data Index: 5315938 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.8863. Min Range: -3.8863

Max Act: 3.6461. Min Act: -0.1700

Data Index: 8107628 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 3.8863. Min Range: -3.8863

Max Act: 3.6636. Min Act: -0.1700

Data Index: 4481950 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 3.8863. Min Range: -3.8863

Max Act: 3.6380. Min Act: -0.1700

Data Index: 6567621 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.8863. Min Range: -3.8863

Max Act: 3.6213. Min Act: -0.1700

Data Index: 3006456 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.8863. Min Range: -3.8863

Max Act: 3.6208. Min Act: -0.1700

Data Index: 2273520 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.8863. Min Range: -3.8863

Max Act: 3.6371. Min Act: -0.1700

Data Index: 5318093 (Open Web Text)

Max Activating Token Index: 28

Text #13

Max Range: 3.8863. Min Range: -3.8863

Max Act: 3.6391. Min Act: -0.1700

Data Index: 7330967 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 3.8863. Min Range: -3.8863

Max Act: 3.6161. Min Act: -0.1700

Data Index: 6776862 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.8863. Min Range: -3.8863

Max Act: 3.6029. Min Act: -0.1700

Data Index: 55231 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.8863. Min Range: -3.8863

Max Act: 3.5988. Min Act: -0.1700

Data Index: 2835973 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.8863. Min Range: -3.8863

Max Act: 3.5855. Min Act: -0.1700

Data Index: 5086499 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.8863. Min Range: -3.8863

Max Act: 3.5990. Min Act: -0.1700

Data Index: 5299388 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.8863. Min Range: -3.8863

Max Act: 3.5875. Min Act: -0.1700

Data Index: 5755137 (Open Web Text)

Max Activating Token Index: 5