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

Dataset: Open Web Text

Neuron 2244 in Layer 6

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: 3.8851. Min Range: -3.8851

Max Act: 3.8851. Min Act: -0.1700

Data Index: 2241222 (Open Web Text)

Max Activating Token Index: 352

Text #1

Max Range: 3.8851. Min Range: -3.8851

Max Act: 3.8336. Min Act: -0.1700

Data Index: 3791415 (Open Web Text)

Max Activating Token Index: 313

Text #2

Max Range: 3.8851. Min Range: -3.8851

Max Act: 3.8220. Min Act: -0.1700

Data Index: 2066885 (Open Web Text)

Max Activating Token Index: 59

Text #3

Max Range: 3.8851. Min Range: -3.8851

Max Act: 3.8214. Min Act: -0.1700

Data Index: 6654344 (Open Web Text)

Max Activating Token Index: 864

Text #4

Max Range: 3.8851. Min Range: -3.8851

Max Act: 3.7862. Min Act: -0.1700

Data Index: 7743647 (Open Web Text)

Max Activating Token Index: 432

Text #5

Max Range: 3.8851. Min Range: -3.8851

Max Act: 3.7956. Min Act: -0.1700

Data Index: 7558380 (Open Web Text)

Max Activating Token Index: 838

Text #6

Max Range: 3.8851. Min Range: -3.8851

Max Act: 3.7600. Min Act: -0.1700

Data Index: 2748212 (Open Web Text)

Max Activating Token Index: 428

Text #7

Max Range: 3.8851. Min Range: -3.8851

Max Act: 3.7547. Min Act: -0.1700

Data Index: 6791857 (Open Web Text)

Max Activating Token Index: 153

Text #8

Max Range: 3.8851. Min Range: -3.8851

Max Act: 3.7811. Min Act: -0.1700

Data Index: 793698 (Open Web Text)

Max Activating Token Index: 671

Text #9

Max Range: 3.8851. Min Range: -3.8851

Max Act: 3.7419. Min Act: -0.1700

Data Index: 6472840 (Open Web Text)

Max Activating Token Index: 599

Text #10

Max Range: 3.8851. Min Range: -3.8851

Max Act: 3.7559. Min Act: -0.1700

Data Index: 7083433 (Open Web Text)

Max Activating Token Index: 740

Text #11

Max Range: 3.8851. Min Range: -3.8851

Max Act: 3.7375. Min Act: -0.1700

Data Index: 2066883 (Open Web Text)

Max Activating Token Index: 649

Text #12

Max Range: 3.8851. Min Range: -3.8851

Max Act: 3.7319. Min Act: -0.1700

Data Index: 4229131 (Open Web Text)

Max Activating Token Index: 70

Text #13

Max Range: 3.8851. Min Range: -3.8851

Max Act: 3.7308. Min Act: -0.1700

Data Index: 5285869 (Open Web Text)

Max Activating Token Index: 923

Text #14

Max Range: 3.8851. Min Range: -3.8851

Max Act: 3.7191. Min Act: -0.1700

Data Index: 3011021 (Open Web Text)

Max Activating Token Index: 394

Text #15

Max Range: 3.8851. Min Range: -3.8851

Max Act: 3.7243. Min Act: -0.1700

Data Index: 4017379 (Open Web Text)

Max Activating Token Index: 844

Text #16

Max Range: 3.8851. Min Range: -3.8851

Max Act: 3.7026. Min Act: -0.1700

Data Index: 5889450 (Open Web Text)

Max Activating Token Index: 76

Text #17

Max Range: 3.8851. Min Range: -3.8851

Max Act: 3.7087. Min Act: -0.1700

Data Index: 3904959 (Open Web Text)

Max Activating Token Index: 301

Text #18

Max Range: 3.8851. Min Range: -3.8851

Max Act: 3.6948. Min Act: -0.1700

Data Index: 2982509 (Open Web Text)

Max Activating Token Index: 39

Text #19

Max Range: 3.8851. Min Range: -3.8851

Max Act: 3.6744. Min Act: -0.1700

Data Index: 1663012 (Open Web Text)

Max Activating Token Index: 490