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

Dataset: Open Web Text

Neuron 1668 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: 4.6869. Min Range: -4.6869

Max Act: 4.6869. Min Act: -0.1700

Data Index: 8158330 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.6869. Min Range: -4.6869

Max Act: 4.6386. Min Act: -0.1700

Data Index: 1513548 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.6869. Min Range: -4.6869

Max Act: 4.6244. Min Act: -0.1700

Data Index: 8691861 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 4.6869. Min Range: -4.6869

Max Act: 4.6258. Min Act: -0.1700

Data Index: 5129982 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.6869. Min Range: -4.6869

Max Act: 4.6340. Min Act: -0.1700

Data Index: 7154305 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 4.6869. Min Range: -4.6869

Max Act: 4.6333. Min Act: -0.1700

Data Index: 6927791 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.6869. Min Range: -4.6869

Max Act: 4.6030. Min Act: -0.1700

Data Index: 7906165 (Open Web Text)

Max Activating Token Index: 44

Text #7

Max Range: 4.6869. Min Range: -4.6869

Max Act: 4.6227. Min Act: -0.1700

Data Index: 4040657 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.6869. Min Range: -4.6869

Max Act: 4.6074. Min Act: -0.1700

Data Index: 3044612 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 4.6869. Min Range: -4.6869

Max Act: 4.5816. Min Act: -0.1700

Data Index: 3359026 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 4.6869. Min Range: -4.6869

Max Act: 4.5900. Min Act: -0.1700

Data Index: 1777545 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.6869. Min Range: -4.6869

Max Act: 4.5749. Min Act: -0.1700

Data Index: 7033238 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.6869. Min Range: -4.6869

Max Act: 4.5853. Min Act: -0.1700

Data Index: 8661345 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 4.6869. Min Range: -4.6869

Max Act: 4.5888. Min Act: -0.1700

Data Index: 5664936 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 4.6869. Min Range: -4.6869

Max Act: 4.5986. Min Act: -0.1700

Data Index: 5608065 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.6869. Min Range: -4.6869

Max Act: 4.5450. Min Act: -0.1700

Data Index: 1952469 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 4.6869. Min Range: -4.6869

Max Act: 4.5345. Min Act: -0.1700

Data Index: 2050714 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.6869. Min Range: -4.6869

Max Act: 4.5461. Min Act: -0.1700

Data Index: 5450302 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 4.6869. Min Range: -4.6869

Max Act: 4.5347. Min Act: -0.1700

Data Index: 5491736 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.6869. Min Range: -4.6869

Max Act: 4.5367. Min Act: -0.1700

Data Index: 2597564 (Open Web Text)

Max Activating Token Index: 7