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

Dataset: Open Web Text

Neuron 493 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: 6.1643. Min Range: -6.1643

Max Act: 6.1643. Min Act: -0.1700

Data Index: 8832345 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 6.1643. Min Range: -6.1643

Max Act: 6.1310. Min Act: -0.1700

Data Index: 275358 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 6.1643. Min Range: -6.1643

Max Act: 6.1142. Min Act: -0.1700

Data Index: 7169377 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 6.1643. Min Range: -6.1643

Max Act: 6.0761. Min Act: -0.1700

Data Index: 2994391 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 6.1643. Min Range: -6.1643

Max Act: 6.0730. Min Act: -0.1700

Data Index: 7891444 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 6.1643. Min Range: -6.1643

Max Act: 6.0298. Min Act: -0.1700

Data Index: 3597556 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 6.1643. Min Range: -6.1643

Max Act: 6.0265. Min Act: -0.1700

Data Index: 4253722 (Open Web Text)

Max Activating Token Index: 26

Text #7

Max Range: 6.1643. Min Range: -6.1643

Max Act: 6.0484. Min Act: -0.1700

Data Index: 4599864 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 6.1643. Min Range: -6.1643

Max Act: 6.0466. Min Act: -0.1700

Data Index: 5838610 (Open Web Text)

Max Activating Token Index: 10

Text #9

Max Range: 6.1643. Min Range: -6.1643

Max Act: 6.0347. Min Act: -0.1700

Data Index: 4680308 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 6.1643. Min Range: -6.1643

Max Act: 6.0075. Min Act: -0.1700

Data Index: 6751035 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 6.1643. Min Range: -6.1643

Max Act: 5.9929. Min Act: -0.1700

Data Index: 378240 (Open Web Text)

Max Activating Token Index: 28

Text #12

Max Range: 6.1643. Min Range: -6.1643

Max Act: 6.0043. Min Act: -0.1700

Data Index: 3257925 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 6.1643. Min Range: -6.1643

Max Act: 5.9972. Min Act: -0.1700

Data Index: 5530115 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 6.1643. Min Range: -6.1643

Max Act: 6.0018. Min Act: -0.1700

Data Index: 5766534 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 6.1643. Min Range: -6.1643

Max Act: 6.0116. Min Act: -0.1700

Data Index: 3043874 (Open Web Text)

Max Activating Token Index: 17

Text #16

Max Range: 6.1643. Min Range: -6.1643

Max Act: 5.9924. Min Act: -0.1700

Data Index: 1580621 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 6.1643. Min Range: -6.1643

Max Act: 5.9918. Min Act: -0.1700

Data Index: 4017301 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 6.1643. Min Range: -6.1643

Max Act: 6.0211. Min Act: -0.1700

Data Index: 3934947 (Open Web Text)

Max Activating Token Index: 17

Text #19

Max Range: 6.1643. Min Range: -6.1643

Max Act: 5.9876. Min Act: -0.1700

Data Index: 6446109 (Open Web Text)

Max Activating Token Index: 5