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

Dataset: Open Web Text

Neuron 181 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: 4.8585. Min Range: -4.8585

Max Act: 4.8585. Min Act: -0.1700

Data Index: 7027041 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.7994. Min Act: -0.1700

Data Index: 5559257 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.7853. Min Act: -0.1700

Data Index: 5869707 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.7685. Min Act: -0.1700

Data Index: 3943904 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.7732. Min Act: -0.1700

Data Index: 8518270 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.7509. Min Act: -0.1700

Data Index: 1397911 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.7636. Min Act: -0.1700

Data Index: 4466581 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.7662. Min Act: -0.1700

Data Index: 5879772 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.7142. Min Act: -0.1700

Data Index: 4831389 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.7294. Min Act: -0.1700

Data Index: 5097723 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.7400. Min Act: -0.1700

Data Index: 8468618 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.7210. Min Act: -0.1700

Data Index: 8082146 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.7321. Min Act: -0.1700

Data Index: 4273154 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.7287. Min Act: -0.1700

Data Index: 3722537 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.7135. Min Act: -0.1700

Data Index: 7155698 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.7327. Min Act: -0.1700

Data Index: 5850782 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.7378. Min Act: -0.1700

Data Index: 3382173 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.7069. Min Act: -0.1700

Data Index: 6609885 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.7127. Min Act: -0.1700

Data Index: 5097773 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 4.8585. Min Range: -4.8585

Max Act: 4.7173. Min Act: -0.1700

Data Index: 6018120 (Open Web Text)

Max Activating Token Index: 6