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

Dataset: Open Web Text

Neuron 1522 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: 2.5938. Min Range: -2.5938

Max Act: 2.5938. Min Act: -0.1700

Data Index: 4965487 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.5835. Min Act: -0.1700

Data Index: 7545874 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.5889. Min Act: -0.1700

Data Index: 689176 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.5617. Min Act: -0.1700

Data Index: 1549001 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.5808. Min Act: -0.1700

Data Index: 1870093 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.5681. Min Act: -0.1700

Data Index: 4112847 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.5811. Min Act: -0.1700

Data Index: 3705369 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.5752. Min Act: -0.1700

Data Index: 7781216 (Open Web Text)

Max Activating Token Index: 12

Text #8

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.5497. Min Act: -0.1700

Data Index: 2353554 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.5536. Min Act: -0.1699

Data Index: 8423761 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.5613. Min Act: -0.1700

Data Index: 7971563 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.5640. Min Act: -0.1700

Data Index: 994516 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.5480. Min Act: -0.1699

Data Index: 7743742 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.5598. Min Act: -0.1693

Data Index: 5115024 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.5435. Min Act: -0.1699

Data Index: 2296472 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.5361. Min Act: -0.1700

Data Index: 684022 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.5327. Min Act: -0.1700

Data Index: 384980 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.5268. Min Act: -0.1697

Data Index: 4235318 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.5128. Min Act: -0.1700

Data Index: 65376 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.5938. Min Range: -2.5938

Max Act: 2.5294. Min Act: -0.1700

Data Index: 943196 (Open Web Text)

Max Activating Token Index: 7