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

Dataset: Open Web Text

Neuron 1124 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: 3.5389. Min Range: -3.5389

Max Act: 3.5389. Min Act: -0.1700

Data Index: 8105668 (Open Web Text)

Max Activating Token Index: 16

Text #1

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.4922. Min Act: -0.1700

Data Index: 6378766 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.5059. Min Act: -0.1700

Data Index: 3151805 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.4816. Min Act: -0.1700

Data Index: 2419793 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.4482. Min Act: -0.1700

Data Index: 5112799 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.4252. Min Act: -0.1700

Data Index: 1487734 (Open Web Text)

Max Activating Token Index: 13

Text #6

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.4139. Min Act: -0.1700

Data Index: 8702821 (Open Web Text)

Max Activating Token Index: 26

Text #7

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.4161. Min Act: -0.1700

Data Index: 2962860 (Open Web Text)

Max Activating Token Index: 18

Text #8

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.4180. Min Act: -0.1700

Data Index: 2090196 (Open Web Text)

Max Activating Token Index: 32

Text #9

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.4244. Min Act: -0.1700

Data Index: 8278216 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.3978. Min Act: -0.1700

Data Index: 3840751 (Open Web Text)

Max Activating Token Index: 279

Text #11

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.4083. Min Act: -0.1700

Data Index: 1373451 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.3849. Min Act: -0.1700

Data Index: 3942708 (Open Web Text)

Max Activating Token Index: 802

Text #13

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.3872. Min Act: -0.1700

Data Index: 731851 (Open Web Text)

Max Activating Token Index: 14

Text #14

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.4106. Min Act: -0.1700

Data Index: 4635429 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.3997. Min Act: -0.1700

Data Index: 910913 (Open Web Text)

Max Activating Token Index: 109

Text #16

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.3950. Min Act: -0.1700

Data Index: 6942890 (Open Web Text)

Max Activating Token Index: 804

Text #17

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.4012. Min Act: -0.1700

Data Index: 7415012 (Open Web Text)

Max Activating Token Index: 652

Text #18

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.3943. Min Act: -0.1700

Data Index: 921336 (Open Web Text)

Max Activating Token Index: 32

Text #19

Max Range: 3.5389. Min Range: -3.5389

Max Act: 3.3828. Min Act: -0.1700

Data Index: 7868468 (Open Web Text)

Max Activating Token Index: 11