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

Dataset: Open Web Text

Neuron 2133 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: 2.4607. Min Range: -2.4607

Max Act: 2.4607. Min Act: -0.1700

Data Index: 6068001 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 2.4607. Min Range: -2.4607

Max Act: 2.4462. Min Act: -0.1700

Data Index: 3433031 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 2.4607. Min Range: -2.4607

Max Act: 2.4285. Min Act: -0.1700

Data Index: 2449766 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 2.4607. Min Range: -2.4607

Max Act: 2.4356. Min Act: -0.1700

Data Index: 2207408 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 2.4607. Min Range: -2.4607

Max Act: 2.4251. Min Act: -0.1700

Data Index: 6724737 (Open Web Text)

Max Activating Token Index: 31

Text #5

Max Range: 2.4607. Min Range: -2.4607

Max Act: 2.4085. Min Act: -0.1700

Data Index: 8442879 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.4607. Min Range: -2.4607

Max Act: 2.4084. Min Act: -0.1700

Data Index: 5426869 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 2.4607. Min Range: -2.4607

Max Act: 2.4109. Min Act: -0.1700

Data Index: 2158128 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 2.4607. Min Range: -2.4607

Max Act: 2.4109. Min Act: -0.1700

Data Index: 4395670 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 2.4607. Min Range: -2.4607

Max Act: 2.4085. Min Act: -0.1700

Data Index: 5115475 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 2.4607. Min Range: -2.4607

Max Act: 2.4085. Min Act: -0.1700

Data Index: 5777449 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 2.4607. Min Range: -2.4607

Max Act: 2.3826. Min Act: -0.1700

Data Index: 6538705 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.4607. Min Range: -2.4607

Max Act: 2.3863. Min Act: -0.1700

Data Index: 421233 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 2.4607. Min Range: -2.4607

Max Act: 2.3779. Min Act: -0.1700

Data Index: 339087 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 2.4607. Min Range: -2.4607

Max Act: 2.3687. Min Act: -0.1700

Data Index: 8538630 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 2.4607. Min Range: -2.4607

Max Act: 2.3701. Min Act: -0.1700

Data Index: 2086930 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 2.4607. Min Range: -2.4607

Max Act: 2.3625. Min Act: -0.1700

Data Index: 6991626 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 2.4607. Min Range: -2.4607

Max Act: 2.3518. Min Act: -0.1700

Data Index: 7171700 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 2.4607. Min Range: -2.4607

Max Act: 2.3464. Min Act: -0.1700

Data Index: 179369 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 2.4607. Min Range: -2.4607

Max Act: 2.3501. Min Act: -0.1700

Data Index: 4350598 (Open Web Text)

Max Activating Token Index: 9