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

Dataset: Open Web Text

Neuron 1905 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: 3.1180. Min Range: -3.1180

Max Act: 3.1169. Min Act: -0.1700

Data Index: 839977 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.1180. Min Range: -3.1180

Max Act: 3.1158. Min Act: -0.1700

Data Index: 2691335 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 3.1180. Min Range: -3.1180

Max Act: 3.1180. Min Act: -0.1700

Data Index: 155279 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.1180. Min Range: -3.1180

Max Act: 3.0936. Min Act: -0.1700

Data Index: 2484477 (Open Web Text)

Max Activating Token Index: 535

Text #4

Max Range: 3.1180. Min Range: -3.1180

Max Act: 3.0887. Min Act: -0.1700

Data Index: 1447634 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 3.1180. Min Range: -3.1180

Max Act: 3.0875. Min Act: -0.1700

Data Index: 271884 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.1180. Min Range: -3.1180

Max Act: 3.0961. Min Act: -0.1700

Data Index: 7279803 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.1180. Min Range: -3.1180

Max Act: 3.0849. Min Act: -0.1700

Data Index: 6920018 (Open Web Text)

Max Activating Token Index: 1012

Text #8

Max Range: 3.1180. Min Range: -3.1180

Max Act: 3.0802. Min Act: -0.1700

Data Index: 1644590 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.1180. Min Range: -3.1180

Max Act: 3.0924. Min Act: -0.1700

Data Index: 3524325 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 3.1180. Min Range: -3.1180

Max Act: 3.0892. Min Act: -0.1700

Data Index: 2634663 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.1180. Min Range: -3.1180

Max Act: 3.0820. Min Act: -0.1700

Data Index: 1000825 (Open Web Text)

Max Activating Token Index: 28

Text #12

Max Range: 3.1180. Min Range: -3.1180

Max Act: 3.0967. Min Act: -0.1700

Data Index: 1516882 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.1180. Min Range: -3.1180

Max Act: 3.0823. Min Act: -0.1700

Data Index: 6717729 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 3.1180. Min Range: -3.1180

Max Act: 3.0651. Min Act: -0.1700

Data Index: 6914768 (Open Web Text)

Max Activating Token Index: 956

Text #15

Max Range: 3.1180. Min Range: -3.1180

Max Act: 3.0790. Min Act: -0.1700

Data Index: 383201 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 3.1180. Min Range: -3.1180

Max Act: 3.0733. Min Act: -0.1700

Data Index: 4328599 (Open Web Text)

Max Activating Token Index: 517

Text #17

Max Range: 3.1180. Min Range: -3.1180

Max Act: 3.0759. Min Act: -0.1700

Data Index: 1482098 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.1180. Min Range: -3.1180

Max Act: 3.0771. Min Act: -0.1700

Data Index: 8137569 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.1180. Min Range: -3.1180

Max Act: 3.0740. Min Act: -0.1700

Data Index: 480274 (Open Web Text)

Max Activating Token Index: 4