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

Dataset: Open Web Text

Neuron 1465 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: 4.1542. Min Range: -4.1542

Max Act: 4.1542. Min Act: -0.1700

Data Index: 3336888 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 4.1542. Min Range: -4.1542

Max Act: 4.0849. Min Act: -0.1700

Data Index: 8248602 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 4.1542. Min Range: -4.1542

Max Act: 4.0735. Min Act: -0.1700

Data Index: 4553784 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.1542. Min Range: -4.1542

Max Act: 4.0788. Min Act: -0.1700

Data Index: 3711715 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.1542. Min Range: -4.1542

Max Act: 4.0298. Min Act: -0.1700

Data Index: 4691371 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 4.1542. Min Range: -4.1542

Max Act: 4.0115. Min Act: -0.1700

Data Index: 6100793 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 4.1542. Min Range: -4.1542

Max Act: 3.9872. Min Act: -0.1700

Data Index: 877092 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.1542. Min Range: -4.1542

Max Act: 3.9808. Min Act: -0.1700

Data Index: 810337 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.1542. Min Range: -4.1542

Max Act: 3.9872. Min Act: -0.1700

Data Index: 5844134 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.1542. Min Range: -4.1542

Max Act: 3.9763. Min Act: -0.1700

Data Index: 737688 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.1542. Min Range: -4.1542

Max Act: 3.9623. Min Act: -0.1700

Data Index: 24067 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 4.1542. Min Range: -4.1542

Max Act: 3.9413. Min Act: -0.1700

Data Index: 1573200 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 4.1542. Min Range: -4.1542

Max Act: 3.8981. Min Act: -0.1700

Data Index: 6185022 (Open Web Text)

Max Activating Token Index: 1012

Text #13

Max Range: 4.1542. Min Range: -4.1542

Max Act: 3.9233. Min Act: -0.1700

Data Index: 6866587 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 4.1542. Min Range: -4.1542

Max Act: 3.8979. Min Act: -0.1700

Data Index: 1412624 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 4.1542. Min Range: -4.1542

Max Act: 3.9085. Min Act: -0.1700

Data Index: 1376926 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.1542. Min Range: -4.1542

Max Act: 3.8935. Min Act: -0.1700

Data Index: 2939694 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.1542. Min Range: -4.1542

Max Act: 3.8873. Min Act: -0.1700

Data Index: 3948564 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.1542. Min Range: -4.1542

Max Act: 3.8896. Min Act: -0.1700

Data Index: 330578 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 4.1542. Min Range: -4.1542

Max Act: 3.8920. Min Act: -0.1700

Data Index: 1748311 (Open Web Text)

Max Activating Token Index: 5