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

Dataset: Open Web Text

Neuron 2874 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: 6.2195. Min Range: -6.2195

Max Act: 6.2195. Min Act: -0.1700

Data Index: 5048815 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 6.2195. Min Range: -6.2195

Max Act: 6.2166. Min Act: -0.1700

Data Index: 2715544 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 6.2195. Min Range: -6.2195

Max Act: 6.1260. Min Act: -0.1700

Data Index: 4878602 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 6.2195. Min Range: -6.2195

Max Act: 6.1339. Min Act: -0.1700

Data Index: 7530774 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 6.2195. Min Range: -6.2195

Max Act: 6.1278. Min Act: -0.1700

Data Index: 6716557 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 6.2195. Min Range: -6.2195

Max Act: 6.0900. Min Act: -0.1700

Data Index: 1547373 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 6.2195. Min Range: -6.2195

Max Act: 6.0972. Min Act: -0.1700

Data Index: 4837803 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 6.2195. Min Range: -6.2195

Max Act: 6.0868. Min Act: -0.1700

Data Index: 7936931 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 6.2195. Min Range: -6.2195

Max Act: 6.0719. Min Act: -0.1700

Data Index: 6403071 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 6.2195. Min Range: -6.2195

Max Act: 6.0899. Min Act: -0.1700

Data Index: 5862150 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 6.2195. Min Range: -6.2195

Max Act: 6.0766. Min Act: -0.1700

Data Index: 1547378 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 6.2195. Min Range: -6.2195

Max Act: 6.0812. Min Act: -0.1700

Data Index: 922479 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 6.2195. Min Range: -6.2195

Max Act: 6.0603. Min Act: -0.1700

Data Index: 3607867 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 6.2195. Min Range: -6.2195

Max Act: 6.0639. Min Act: -0.1700

Data Index: 2307079 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 6.2195. Min Range: -6.2195

Max Act: 6.0674. Min Act: -0.1700

Data Index: 76440 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 6.2195. Min Range: -6.2195

Max Act: 6.0611. Min Act: -0.1700

Data Index: 9015 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 6.2195. Min Range: -6.2195

Max Act: 6.0613. Min Act: -0.1700

Data Index: 189717 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 6.2195. Min Range: -6.2195

Max Act: 6.0464. Min Act: -0.1700

Data Index: 3687468 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 6.2195. Min Range: -6.2195

Max Act: 6.0464. Min Act: -0.1700

Data Index: 613168 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 6.2195. Min Range: -6.2195

Max Act: 6.0626. Min Act: -0.1700

Data Index: 3942251 (Open Web Text)

Max Activating Token Index: 5