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

Dataset: Open Web Text

Neuron 1580 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: 3.8098. Min Range: -3.8098

Max Act: 3.8098. Min Act: -0.1700

Data Index: 3170383 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.6850. Min Act: -0.1700

Data Index: 534016 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.6990. Min Act: -0.1700

Data Index: 1876307 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.6815. Min Act: -0.1700

Data Index: 4647357 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.6766. Min Act: -0.1700

Data Index: 7953412 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.6766. Min Act: -0.1700

Data Index: 7736742 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.6713. Min Act: -0.1700

Data Index: 6961411 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.6749. Min Act: -0.1700

Data Index: 3716930 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.6757. Min Act: -0.1700

Data Index: 6957123 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.6831. Min Act: -0.1700

Data Index: 3698204 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.6722. Min Act: -0.1700

Data Index: 6590100 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.6593. Min Act: -0.1700

Data Index: 5815234 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.6732. Min Act: -0.1700

Data Index: 1962792 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.6569. Min Act: -0.1700

Data Index: 8278564 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.6331. Min Act: -0.1700

Data Index: 6802114 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.6173. Min Act: -0.1700

Data Index: 6647257 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.6222. Min Act: -0.1700

Data Index: 669243 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.6242. Min Act: -0.1700

Data Index: 158733 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.6316. Min Act: -0.1700

Data Index: 3013506 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.8098. Min Range: -3.8098

Max Act: 3.6295. Min Act: -0.1700

Data Index: 5096993 (Open Web Text)

Max Activating Token Index: 4