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

Dataset: Open Web Text

Neuron 2744 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: 4.0879. Min Range: -4.0879

Max Act: 4.0879. Min Act: -0.1700

Data Index: 4547079 (Open Web Text)

Max Activating Token Index: 26

Text #1

Max Range: 4.0879. Min Range: -4.0879

Max Act: 4.0671. Min Act: -0.1700

Data Index: 7963592 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 4.0879. Min Range: -4.0879

Max Act: 4.0587. Min Act: -0.1700

Data Index: 771617 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.0879. Min Range: -4.0879

Max Act: 4.0343. Min Act: -0.1700

Data Index: 70221 (Open Web Text)

Max Activating Token Index: 19

Text #4

Max Range: 4.0879. Min Range: -4.0879

Max Act: 4.0255. Min Act: -0.1700

Data Index: 7193005 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 4.0879. Min Range: -4.0879

Max Act: 4.0240. Min Act: -0.1700

Data Index: 6605814 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 4.0879. Min Range: -4.0879

Max Act: 4.0077. Min Act: -0.1700

Data Index: 5906956 (Open Web Text)

Max Activating Token Index: 945

Text #7

Max Range: 4.0879. Min Range: -4.0879

Max Act: 4.0066. Min Act: -0.1700

Data Index: 4710689 (Open Web Text)

Max Activating Token Index: 23

Text #8

Max Range: 4.0879. Min Range: -4.0879

Max Act: 4.0378. Min Act: -0.1700

Data Index: 8461019 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.0879. Min Range: -4.0879

Max Act: 4.0052. Min Act: -0.1700

Data Index: 6088376 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 4.0879. Min Range: -4.0879

Max Act: 3.9931. Min Act: -0.1700

Data Index: 6402676 (Open Web Text)

Max Activating Token Index: 19

Text #11

Max Range: 4.0879. Min Range: -4.0879

Max Act: 3.9709. Min Act: -0.1700

Data Index: 4917242 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 4.0879. Min Range: -4.0879

Max Act: 4.0066. Min Act: -0.1700

Data Index: 4865951 (Open Web Text)

Max Activating Token Index: 20

Text #13

Max Range: 4.0879. Min Range: -4.0879

Max Act: 3.9778. Min Act: -0.1700

Data Index: 858040 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 4.0879. Min Range: -4.0879

Max Act: 3.9966. Min Act: -0.1700

Data Index: 452663 (Open Web Text)

Max Activating Token Index: 35

Text #15

Max Range: 4.0879. Min Range: -4.0879

Max Act: 3.9725. Min Act: -0.1700

Data Index: 3138550 (Open Web Text)

Max Activating Token Index: 21

Text #16

Max Range: 4.0879. Min Range: -4.0879

Max Act: 3.9924. Min Act: -0.1700

Data Index: 3196358 (Open Web Text)

Max Activating Token Index: 37

Text #17

Max Range: 4.0879. Min Range: -4.0879

Max Act: 3.9725. Min Act: -0.1700

Data Index: 3593050 (Open Web Text)

Max Activating Token Index: 18

Text #18

Max Range: 4.0879. Min Range: -4.0879

Max Act: 3.9944. Min Act: -0.1700

Data Index: 6769581 (Open Web Text)

Max Activating Token Index: 21

Text #19

Max Range: 4.0879. Min Range: -4.0879

Max Act: 3.9857. Min Act: -0.1700

Data Index: 7730996 (Open Web Text)

Max Activating Token Index: 5