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

Dataset: Open Web Text

Neuron 2415 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: 2.3899. Min Range: -2.3899

Max Act: 2.3899. Min Act: -0.1700

Data Index: 1884908 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 2.3899. Min Range: -2.3899

Max Act: 2.3793. Min Act: -0.1700

Data Index: 7557681 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.3899. Min Range: -2.3899

Max Act: 2.3793. Min Act: -0.1700

Data Index: 3618527 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 2.3899. Min Range: -2.3899

Max Act: 2.3561. Min Act: -0.1700

Data Index: 2213900 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.3899. Min Range: -2.3899

Max Act: 2.3456. Min Act: -0.1700

Data Index: 4022586 (Open Web Text)

Max Activating Token Index: 577

Text #5

Max Range: 2.3899. Min Range: -2.3899

Max Act: 2.3453. Min Act: -0.1700

Data Index: 4086271 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 2.3899. Min Range: -2.3899

Max Act: 2.3556. Min Act: -0.1700

Data Index: 2356393 (Open Web Text)

Max Activating Token Index: 126

Text #7

Max Range: 2.3899. Min Range: -2.3899

Max Act: 2.3311. Min Act: -0.1700

Data Index: 1886559 (Open Web Text)

Max Activating Token Index: 64

Text #8

Max Range: 2.3899. Min Range: -2.3899

Max Act: 2.3374. Min Act: -0.1700

Data Index: 4773921 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 2.3899. Min Range: -2.3899

Max Act: 2.3380. Min Act: -0.1700

Data Index: 7521572 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 2.3899. Min Range: -2.3899

Max Act: 2.3387. Min Act: -0.1700

Data Index: 2001066 (Open Web Text)

Max Activating Token Index: 670

Text #11

Max Range: 2.3899. Min Range: -2.3899

Max Act: 2.3357. Min Act: -0.1700

Data Index: 2403471 (Open Web Text)

Max Activating Token Index: 100

Text #12

Max Range: 2.3899. Min Range: -2.3899

Max Act: 2.3291. Min Act: -0.1700

Data Index: 6711659 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 2.3899. Min Range: -2.3899

Max Act: 2.3355. Min Act: -0.1700

Data Index: 1895170 (Open Web Text)

Max Activating Token Index: 371

Text #14

Max Range: 2.3899. Min Range: -2.3899

Max Act: 2.3347. Min Act: -0.1700

Data Index: 6390798 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 2.3899. Min Range: -2.3899

Max Act: 2.3298. Min Act: -0.1700

Data Index: 1460963 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 2.3899. Min Range: -2.3899

Max Act: 2.3347. Min Act: -0.1700

Data Index: 5302451 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 2.3899. Min Range: -2.3899

Max Act: 2.3294. Min Act: -0.1700

Data Index: 4055426 (Open Web Text)

Max Activating Token Index: 17

Text #18

Max Range: 2.3899. Min Range: -2.3899

Max Act: 2.3325. Min Act: -0.1700

Data Index: 5790917 (Open Web Text)

Max Activating Token Index: 246

Text #19

Max Range: 2.3899. Min Range: -2.3899

Max Act: 2.3380. Min Act: -0.1700

Data Index: 3803736 (Open Web Text)

Max Activating Token Index: 4