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

Dataset: Open Web Text

Neuron 764 in Layer 1

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: 1.6584. Min Range: -1.6584

Max Act: 1.6584. Min Act: -0.1700

Data Index: 8400314 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.6157. Min Act: -0.1700

Data Index: 6674326 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.5664. Min Act: -0.1700

Data Index: 6681330 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.5537. Min Act: -0.1700

Data Index: 7197762 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.5537. Min Act: -0.1700

Data Index: 3830995 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.5456. Min Act: -0.1700

Data Index: 738089 (Open Web Text)

Max Activating Token Index: 11

Text #6

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.5328. Min Act: -0.1700

Data Index: 6873291 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.5346. Min Act: -0.1700

Data Index: 4768008 (Open Web Text)

Max Activating Token Index: 968

Text #8

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.5358. Min Act: -0.1700

Data Index: 5261567 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.5145. Min Act: -0.1700

Data Index: 7816552 (Open Web Text)

Max Activating Token Index: 464

Text #10

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.5157. Min Act: -0.1700

Data Index: 1265730 (Open Web Text)

Max Activating Token Index: 481

Text #11

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.5207. Min Act: -0.1700

Data Index: 7549136 (Open Web Text)

Max Activating Token Index: 114

Text #12

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.5197. Min Act: -0.1700

Data Index: 3509011 (Open Web Text)

Max Activating Token Index: 562

Text #13

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.5062. Min Act: -0.1700

Data Index: 1847359 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.5068. Min Act: -0.1698

Data Index: 3332096 (Open Web Text)

Max Activating Token Index: 294

Text #15

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.4943. Min Act: -0.1700

Data Index: 1931011 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.5099. Min Act: -0.1700

Data Index: 6784218 (Open Web Text)

Max Activating Token Index: 754

Text #17

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.4983. Min Act: -0.1700

Data Index: 6835991 (Open Web Text)

Max Activating Token Index: 98

Text #18

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.4993. Min Act: -0.1700

Data Index: 396056 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 1.6584. Min Range: -1.6584

Max Act: 1.4955. Min Act: -0.1700

Data Index: 3031765 (Open Web Text)

Max Activating Token Index: 43