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

Dataset: Open Web Text

Neuron 2767 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: 1.1165. Min Range: -1.1165

Max Act: 1.1165. Min Act: -0.1700

Data Index: 3921416 (Open Web Text)

Max Activating Token Index: 18

Text #1

Max Range: 1.1165. Min Range: -1.1165

Max Act: 1.0866. Min Act: -0.1700

Data Index: 8347531 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 1.1165. Min Range: -1.1165

Max Act: 1.0617. Min Act: -0.1700

Data Index: 1972611 (Open Web Text)

Max Activating Token Index: 10

Text #3

Max Range: 1.1165. Min Range: -1.1165

Max Act: 1.0440. Min Act: -0.1700

Data Index: 7082640 (Open Web Text)

Max Activating Token Index: 13

Text #4

Max Range: 1.1165. Min Range: -1.1165

Max Act: 1.0340. Min Act: -0.1700

Data Index: 12300 (Open Web Text)

Max Activating Token Index: 14

Text #5

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.9988. Min Act: -0.1700

Data Index: 3559036 (Open Web Text)

Max Activating Token Index: 13

Text #6

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.9903. Min Act: -0.1700

Data Index: 6479915 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 1.1165. Min Range: -1.1165

Max Act: 1.0006. Min Act: -0.1700

Data Index: 6658089 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.9807. Min Act: -0.1700

Data Index: 4923320 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.9851. Min Act: -0.1700

Data Index: 1428214 (Open Web Text)

Max Activating Token Index: 17

Text #10

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.9921. Min Act: -0.1700

Data Index: 6647378 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.9831. Min Act: -0.1700

Data Index: 6205793 (Open Web Text)

Max Activating Token Index: 40

Text #12

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.9832. Min Act: -0.1700

Data Index: 6905968 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.9764. Min Act: -0.1700

Data Index: 3190211 (Open Web Text)

Max Activating Token Index: 16

Text #14

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.9694. Min Act: -0.1700

Data Index: 6101876 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.9635. Min Act: -0.1700

Data Index: 369379 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.9554. Min Act: -0.1700

Data Index: 7425632 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.9595. Min Act: -0.1700

Data Index: 232223 (Open Web Text)

Max Activating Token Index: 15

Text #18

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.9566. Min Act: -0.1700

Data Index: 7367194 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 1.1165. Min Range: -1.1165

Max Act: 0.9646. Min Act: -0.1700

Data Index: 5412402 (Open Web Text)

Max Activating Token Index: 5