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

Dataset: Open Web Text

Neuron 2006 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: 4.4902. Min Range: -4.4902

Max Act: 4.4902. Min Act: -0.1700

Data Index: 4825409 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 4.4902. Min Range: -4.4902

Max Act: 4.4542. Min Act: -0.1700

Data Index: 4776106 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.4902. Min Range: -4.4902

Max Act: 4.4557. Min Act: -0.1700

Data Index: 8741691 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 4.4902. Min Range: -4.4902

Max Act: 4.4100. Min Act: -0.1700

Data Index: 5659366 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.4902. Min Range: -4.4902

Max Act: 4.4119. Min Act: -0.1700

Data Index: 1127244 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.4902. Min Range: -4.4902

Max Act: 4.3693. Min Act: -0.1700

Data Index: 8558009 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 4.4902. Min Range: -4.4902

Max Act: 4.3433. Min Act: -0.1700

Data Index: 6727730 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.4902. Min Range: -4.4902

Max Act: 4.3412. Min Act: -0.1700

Data Index: 588986 (Open Web Text)

Max Activating Token Index: 922

Text #8

Max Range: 4.4902. Min Range: -4.4902

Max Act: 4.3247. Min Act: -0.1700

Data Index: 1236469 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.4902. Min Range: -4.4902

Max Act: 4.2844. Min Act: -0.1700

Data Index: 3536947 (Open Web Text)

Max Activating Token Index: 18

Text #10

Max Range: 4.4902. Min Range: -4.4902

Max Act: 4.2576. Min Act: -0.1700

Data Index: 3568511 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.4902. Min Range: -4.4902

Max Act: 4.2462. Min Act: -0.1700

Data Index: 6289461 (Open Web Text)

Max Activating Token Index: 957

Text #12

Max Range: 4.4902. Min Range: -4.4902

Max Act: 4.2216. Min Act: -0.1700

Data Index: 1290568 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 4.4902. Min Range: -4.4902

Max Act: 4.2371. Min Act: -0.1700

Data Index: 7768459 (Open Web Text)

Max Activating Token Index: 47

Text #14

Max Range: 4.4902. Min Range: -4.4902

Max Act: 4.2069. Min Act: -0.1700

Data Index: 543100 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 4.4902. Min Range: -4.4902

Max Act: 4.2039. Min Act: -0.1700

Data Index: 1289006 (Open Web Text)

Max Activating Token Index: 19

Text #16

Max Range: 4.4902. Min Range: -4.4902

Max Act: 4.1843. Min Act: -0.1700

Data Index: 4613897 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 4.4902. Min Range: -4.4902

Max Act: 4.1875. Min Act: -0.1700

Data Index: 5472665 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 4.4902. Min Range: -4.4902

Max Act: 4.1852. Min Act: -0.1700

Data Index: 5046147 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 4.4902. Min Range: -4.4902

Max Act: 4.1923. Min Act: -0.1700

Data Index: 4043679 (Open Web Text)

Max Activating Token Index: 7