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

Dataset: Open Web Text

Neuron 2064 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: 3.9839. Min Range: -3.9839

Max Act: 3.9839. Min Act: -0.1700

Data Index: 261574 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.9839. Min Act: -0.1700

Data Index: 6080283 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.9321. Min Act: -0.1700

Data Index: 6420050 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.9428. Min Act: -0.1700

Data Index: 7539487 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.8721. Min Act: -0.1700

Data Index: 6260123 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.8898. Min Act: -0.1700

Data Index: 8610326 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.8984. Min Act: -0.1700

Data Index: 2448495 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.8546. Min Act: -0.1700

Data Index: 6977161 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.8463. Min Act: -0.1700

Data Index: 8201627 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.8466. Min Act: -0.1700

Data Index: 6774597 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.8288. Min Act: -0.1700

Data Index: 2258925 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.8153. Min Act: -0.1700

Data Index: 1532977 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.8198. Min Act: -0.1700

Data Index: 8168942 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.8066. Min Act: -0.1700

Data Index: 1863054 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.8238. Min Act: -0.1700

Data Index: 3963755 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.7981. Min Act: -0.1700

Data Index: 2577504 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.7789. Min Act: -0.1700

Data Index: 2895933 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.8031. Min Act: -0.1700

Data Index: 425812 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.7745. Min Act: -0.1700

Data Index: 3814401 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.9839. Min Range: -3.9839

Max Act: 3.7789. Min Act: -0.1700

Data Index: 6351285 (Open Web Text)

Max Activating Token Index: 4