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

Dataset: Open Web Text

Neuron 2280 in Layer 2

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: 3.5821. Min Range: -3.5821

Max Act: 3.5821. Min Act: -0.1700

Data Index: 5333130 (Open Web Text)

Max Activating Token Index: 505

Text #1

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.5496. Min Act: -0.1700

Data Index: 2355589 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.5740. Min Act: -0.1700

Data Index: 7630636 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.5028. Min Act: -0.1700

Data Index: 8207880 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.4750. Min Act: -0.1700

Data Index: 4892036 (Open Web Text)

Max Activating Token Index: 238

Text #5

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.3781. Min Act: -0.1700

Data Index: 2503899 (Open Web Text)

Max Activating Token Index: 128

Text #6

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.3885. Min Act: -0.1700

Data Index: 6611169 (Open Web Text)

Max Activating Token Index: 864

Text #7

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.3431. Min Act: -0.1700

Data Index: 2375574 (Open Web Text)

Max Activating Token Index: 751

Text #8

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.3760. Min Act: -0.1700

Data Index: 8159255 (Open Web Text)

Max Activating Token Index: 405

Text #9

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.3531. Min Act: -0.1700

Data Index: 5048903 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.3095. Min Act: -0.1700

Data Index: 5048889 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.3206. Min Act: -0.1700

Data Index: 8578901 (Open Web Text)

Max Activating Token Index: 69

Text #12

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.2963. Min Act: -0.1700

Data Index: 7656511 (Open Web Text)

Max Activating Token Index: 963

Text #13

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.2772. Min Act: -0.1700

Data Index: 2533523 (Open Web Text)

Max Activating Token Index: 376

Text #14

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.2977. Min Act: -0.1700

Data Index: 1152808 (Open Web Text)

Max Activating Token Index: 698

Text #15

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.2685. Min Act: -0.1700

Data Index: 5227746 (Open Web Text)

Max Activating Token Index: 976

Text #16

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.3207. Min Act: -0.1700

Data Index: 8449448 (Open Web Text)

Max Activating Token Index: 502

Text #17

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.2502. Min Act: -0.1700

Data Index: 8817610 (Open Web Text)

Max Activating Token Index: 76

Text #18

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.2562. Min Act: -0.1700

Data Index: 3183313 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 3.5821. Min Range: -3.5821

Max Act: 3.2181. Min Act: -0.1700

Data Index: 2814447 (Open Web Text)

Max Activating Token Index: 989