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

Dataset: Open Web Text

Neuron 65 in Layer 3

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: 4.2817. Min Range: -4.2817

Max Act: 4.2762. Min Act: -0.1700

Data Index: 5370392 (Open Web Text)

Max Activating Token Index: 65

Text #1

Max Range: 4.2817. Min Range: -4.2817

Max Act: 4.2817. Min Act: -0.1700

Data Index: 5885431 (Open Web Text)

Max Activating Token Index: 793

Text #2

Max Range: 4.2817. Min Range: -4.2817

Max Act: 4.2058. Min Act: -0.1700

Data Index: 3241498 (Open Web Text)

Max Activating Token Index: 102

Text #3

Max Range: 4.2817. Min Range: -4.2817

Max Act: 4.1454. Min Act: -0.1700

Data Index: 7665871 (Open Web Text)

Max Activating Token Index: 867

Text #4

Max Range: 4.2817. Min Range: -4.2817

Max Act: 4.2527. Min Act: -0.1700

Data Index: 2239638 (Open Web Text)

Max Activating Token Index: 456

Text #5

Max Range: 4.2817. Min Range: -4.2817

Max Act: 4.2740. Min Act: -0.1700

Data Index: 8361202 (Open Web Text)

Max Activating Token Index: 847

Text #6

Max Range: 4.2817. Min Range: -4.2817

Max Act: 4.1916. Min Act: -0.1700

Data Index: 1834967 (Open Web Text)

Max Activating Token Index: 427

Text #7

Max Range: 4.2817. Min Range: -4.2817

Max Act: 4.2394. Min Act: -0.1700

Data Index: 1913459 (Open Web Text)

Max Activating Token Index: 877

Text #8

Max Range: 4.2817. Min Range: -4.2817

Max Act: 4.2026. Min Act: -0.1700

Data Index: 7929641 (Open Web Text)

Max Activating Token Index: 1000

Text #9

Max Range: 4.2817. Min Range: -4.2817

Max Act: 4.1751. Min Act: -0.1700

Data Index: 3322275 (Open Web Text)

Max Activating Token Index: 567

Text #10

Max Range: 4.2817. Min Range: -4.2817

Max Act: 4.0859. Min Act: -0.1700

Data Index: 4895713 (Open Web Text)

Max Activating Token Index: 818

Text #11

Max Range: 4.2817. Min Range: -4.2817

Max Act: 4.1256. Min Act: -0.1700

Data Index: 3545784 (Open Web Text)

Max Activating Token Index: 111

Text #12

Max Range: 4.2817. Min Range: -4.2817

Max Act: 4.1688. Min Act: -0.1700

Data Index: 2148564 (Open Web Text)

Max Activating Token Index: 276

Text #13

Max Range: 4.2817. Min Range: -4.2817

Max Act: 4.1065. Min Act: -0.1700

Data Index: 2010396 (Open Web Text)

Max Activating Token Index: 53

Text #14

Max Range: 4.2817. Min Range: -4.2817

Max Act: 4.1589. Min Act: -0.1700

Data Index: 6987415 (Open Web Text)

Max Activating Token Index: 734

Text #15

Max Range: 4.2817. Min Range: -4.2817

Max Act: 4.1361. Min Act: -0.1700

Data Index: 7056014 (Open Web Text)

Max Activating Token Index: 181

Text #16

Max Range: 4.2817. Min Range: -4.2817

Max Act: 4.1647. Min Act: -0.1700

Data Index: 934823 (Open Web Text)

Max Activating Token Index: 175

Text #17

Max Range: 4.2817. Min Range: -4.2817

Max Act: 4.0548. Min Act: -0.1700

Data Index: 780856 (Open Web Text)

Max Activating Token Index: 556

Text #18

Max Range: 4.2817. Min Range: -4.2817

Max Act: 4.0726. Min Act: -0.1700

Data Index: 2057569 (Open Web Text)

Max Activating Token Index: 843

Text #19

Max Range: 4.2817. Min Range: -4.2817

Max Act: 4.0672. Min Act: -0.1700

Data Index: 7084486 (Open Web Text)

Max Activating Token Index: 647