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

Dataset: Open Web Text

Neuron 2364 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: 1.7043. Min Range: -1.7043

Max Act: 1.7043. Min Act: -0.1693

Data Index: 6788258 (Open Web Text)

Max Activating Token Index: 803

Text #1

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.6611. Min Act: -0.1700

Data Index: 2744123 (Open Web Text)

Max Activating Token Index: 674

Text #2

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.6494. Min Act: -0.1691

Data Index: 145601 (Open Web Text)

Max Activating Token Index: 1

Text #3

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.6494. Min Act: -0.1699

Data Index: 5421050 (Open Web Text)

Max Activating Token Index: 1

Text #4

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.6494. Min Act: -0.1700

Data Index: 7582423 (Open Web Text)

Max Activating Token Index: 1

Text #5

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.6494. Min Act: -0.1700

Data Index: 6993647 (Open Web Text)

Max Activating Token Index: 1

Text #6

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.6494. Min Act: -0.1699

Data Index: 4336870 (Open Web Text)

Max Activating Token Index: 1

Text #7

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.6494. Min Act: -0.1700

Data Index: 4164364 (Open Web Text)

Max Activating Token Index: 1

Text #8

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.6494. Min Act: -0.1700

Data Index: 4144064 (Open Web Text)

Max Activating Token Index: 1

Text #9

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.6494. Min Act: -0.1700

Data Index: 636727 (Open Web Text)

Max Activating Token Index: 1

Text #10

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.6494. Min Act: -0.1700

Data Index: 3997197 (Open Web Text)

Max Activating Token Index: 1

Text #11

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.6494. Min Act: -0.1700

Data Index: 2261590 (Open Web Text)

Max Activating Token Index: 1

Text #12

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.6494. Min Act: -0.1683

Data Index: 3604564 (Open Web Text)

Max Activating Token Index: 1

Text #13

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.6494. Min Act: -0.1673

Data Index: 985005 (Open Web Text)

Max Activating Token Index: 1

Text #14

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.6494. Min Act: -0.1700

Data Index: 568667 (Open Web Text)

Max Activating Token Index: 1

Text #15

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.6494. Min Act: -0.1574

Data Index: 5989854 (Open Web Text)

Max Activating Token Index: 1

Text #16

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.6494. Min Act: -0.1698

Data Index: 1627279 (Open Web Text)

Max Activating Token Index: 1

Text #17

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.6494. Min Act: -0.1700

Data Index: 3412149 (Open Web Text)

Max Activating Token Index: 1

Text #18

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.6494. Min Act: -0.1700

Data Index: 5644018 (Open Web Text)

Max Activating Token Index: 1

Text #19

Max Range: 1.7043. Min Range: -1.7043

Max Act: 1.6494. Min Act: -0.1696

Data Index: 2718649 (Open Web Text)

Max Activating Token Index: 1