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

Dataset: Open Web Text

Neuron 220 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: 0.8981. Min Range: -0.8981

Max Act: 0.8981. Min Act: -0.1700

Data Index: 282450 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8981. Min Act: -0.1700

Data Index: 1900238 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8748. Min Act: -0.1700

Data Index: 4194828 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8564. Min Act: -0.1700

Data Index: 1570846 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8509. Min Act: -0.1700

Data Index: 5926140 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8490. Min Act: -0.1700

Data Index: 6120757 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8540. Min Act: -0.1700

Data Index: 8047493 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8509. Min Act: -0.1700

Data Index: 8304117 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8634. Min Act: -0.1700

Data Index: 5477824 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8439. Min Act: -0.1700

Data Index: 491136 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8435. Min Act: -0.1700

Data Index: 8739941 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8309. Min Act: -0.1700

Data Index: 8815387 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8347. Min Act: -0.1700

Data Index: 3986600 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8344. Min Act: -0.1700

Data Index: 1873749 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8344. Min Act: -0.1700

Data Index: 7864920 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8344. Min Act: -0.1700

Data Index: 8433423 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8384. Min Act: -0.1700

Data Index: 2156200 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8344. Min Act: -0.1700

Data Index: 735602 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8367. Min Act: -0.1700

Data Index: 5955137 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 0.8981. Min Range: -0.8981

Max Act: 0.8344. Min Act: -0.1700

Data Index: 846648 (Open Web Text)

Max Activating Token Index: 3