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

Dataset: Open Web Text

Neuron 867 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: 3.3706. Min Range: -3.3706

Max Act: 3.3706. Min Act: -0.1700

Data Index: 728717 (Open Web Text)

Max Activating Token Index: 668

Text #1

Max Range: 3.3706. Min Range: -3.3706

Max Act: 3.3595. Min Act: -0.1700

Data Index: 1995157 (Open Web Text)

Max Activating Token Index: 19

Text #2

Max Range: 3.3706. Min Range: -3.3706

Max Act: 3.2294. Min Act: -0.1700

Data Index: 5415071 (Open Web Text)

Max Activating Token Index: 458

Text #3

Max Range: 3.3706. Min Range: -3.3706

Max Act: 3.2234. Min Act: -0.1700

Data Index: 4098890 (Open Web Text)

Max Activating Token Index: 40

Text #4

Max Range: 3.3706. Min Range: -3.3706

Max Act: 3.2286. Min Act: -0.1700

Data Index: 3751648 (Open Web Text)

Max Activating Token Index: 12

Text #5

Max Range: 3.3706. Min Range: -3.3706

Max Act: 3.2289. Min Act: -0.1700

Data Index: 6823425 (Open Web Text)

Max Activating Token Index: 155

Text #6

Max Range: 3.3706. Min Range: -3.3706

Max Act: 3.2052. Min Act: -0.1700

Data Index: 6708421 (Open Web Text)

Max Activating Token Index: 424

Text #7

Max Range: 3.3706. Min Range: -3.3706

Max Act: 3.1818. Min Act: -0.1700

Data Index: 6457041 (Open Web Text)

Max Activating Token Index: 28

Text #8

Max Range: 3.3706. Min Range: -3.3706

Max Act: 3.1883. Min Act: -0.1700

Data Index: 699903 (Open Web Text)

Max Activating Token Index: 533

Text #9

Max Range: 3.3706. Min Range: -3.3706

Max Act: 3.1930. Min Act: -0.1700

Data Index: 2209412 (Open Web Text)

Max Activating Token Index: 69

Text #10

Max Range: 3.3706. Min Range: -3.3706

Max Act: 3.1732. Min Act: -0.1700

Data Index: 7185867 (Open Web Text)

Max Activating Token Index: 122

Text #11

Max Range: 3.3706. Min Range: -3.3706

Max Act: 3.1756. Min Act: -0.1700

Data Index: 5007312 (Open Web Text)

Max Activating Token Index: 24

Text #12

Max Range: 3.3706. Min Range: -3.3706

Max Act: 3.1597. Min Act: -0.1700

Data Index: 87340 (Open Web Text)

Max Activating Token Index: 325

Text #13

Max Range: 3.3706. Min Range: -3.3706

Max Act: 3.1782. Min Act: -0.1700

Data Index: 8174550 (Open Web Text)

Max Activating Token Index: 439

Text #14

Max Range: 3.3706. Min Range: -3.3706

Max Act: 3.1776. Min Act: -0.1700

Data Index: 7303645 (Open Web Text)

Max Activating Token Index: 442

Text #15

Max Range: 3.3706. Min Range: -3.3706

Max Act: 3.1953. Min Act: -0.1700

Data Index: 993902 (Open Web Text)

Max Activating Token Index: 491

Text #16

Max Range: 3.3706. Min Range: -3.3706

Max Act: 3.1565. Min Act: -0.1700

Data Index: 6521546 (Open Web Text)

Max Activating Token Index: 601

Text #17

Max Range: 3.3706. Min Range: -3.3706

Max Act: 3.1739. Min Act: -0.1700

Data Index: 4908301 (Open Web Text)

Max Activating Token Index: 32

Text #18

Max Range: 3.3706. Min Range: -3.3706

Max Act: 3.1527. Min Act: -0.1700

Data Index: 4636145 (Open Web Text)

Max Activating Token Index: 998

Text #19

Max Range: 3.3706. Min Range: -3.3706

Max Act: 3.1706. Min Act: -0.1700

Data Index: 621255 (Open Web Text)

Max Activating Token Index: 28