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

Dataset: Open Web Text

Neuron 1507 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: 4.0454. Min Range: -4.0454

Max Act: 4.0454. Min Act: -0.1700

Data Index: 1011034 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 4.0454. Min Range: -4.0454

Max Act: 3.9924. Min Act: -0.1700

Data Index: 5542094 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.0454. Min Range: -4.0454

Max Act: 3.9518. Min Act: -0.1700

Data Index: 4397006 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.0454. Min Range: -4.0454

Max Act: 3.9299. Min Act: -0.1700

Data Index: 5297150 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.0454. Min Range: -4.0454

Max Act: 3.9279. Min Act: -0.1700

Data Index: 1007881 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 4.0454. Min Range: -4.0454

Max Act: 3.9276. Min Act: -0.1700

Data Index: 4357350 (Open Web Text)

Max Activating Token Index: 35

Text #6

Max Range: 4.0454. Min Range: -4.0454

Max Act: 3.9082. Min Act: -0.1700

Data Index: 3336349 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.0454. Min Range: -4.0454

Max Act: 3.9082. Min Act: -0.1700

Data Index: 2416900 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 4.0454. Min Range: -4.0454

Max Act: 3.9183. Min Act: -0.1700

Data Index: 7826888 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.0454. Min Range: -4.0454

Max Act: 3.8761. Min Act: -0.1700

Data Index: 7478578 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.0454. Min Range: -4.0454

Max Act: 3.8816. Min Act: -0.1700

Data Index: 1417608 (Open Web Text)

Max Activating Token Index: 35

Text #11

Max Range: 4.0454. Min Range: -4.0454

Max Act: 3.8872. Min Act: -0.1700

Data Index: 6642840 (Open Web Text)

Max Activating Token Index: 14

Text #12

Max Range: 4.0454. Min Range: -4.0454

Max Act: 3.8824. Min Act: -0.1700

Data Index: 4982197 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 4.0454. Min Range: -4.0454

Max Act: 3.8955. Min Act: -0.1700

Data Index: 988963 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.0454. Min Range: -4.0454

Max Act: 3.8893. Min Act: -0.1700

Data Index: 4723982 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.0454. Min Range: -4.0454

Max Act: 3.8726. Min Act: -0.1700

Data Index: 4241557 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 4.0454. Min Range: -4.0454

Max Act: 3.9026. Min Act: -0.1700

Data Index: 6358029 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.0454. Min Range: -4.0454

Max Act: 3.8847. Min Act: -0.1700

Data Index: 6051369 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.0454. Min Range: -4.0454

Max Act: 3.8697. Min Act: -0.1700

Data Index: 1664940 (Open Web Text)

Max Activating Token Index: 15

Text #19

Max Range: 4.0454. Min Range: -4.0454

Max Act: 3.8737. Min Act: -0.1700

Data Index: 891772 (Open Web Text)

Max Activating Token Index: 6