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

Dataset: Open Web Text

Neuron 854 in Layer 6

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: 4.5076. Min Range: -4.5076

Max Act: 4.5076. Min Act: -0.1700

Data Index: 5841042 (Open Web Text)

Max Activating Token Index: 91

Text #1

Max Range: 4.5076. Min Range: -4.5076

Max Act: 4.3753. Min Act: -0.1700

Data Index: 8803142 (Open Web Text)

Max Activating Token Index: 246

Text #2

Max Range: 4.5076. Min Range: -4.5076

Max Act: 4.3470. Min Act: -0.1700

Data Index: 1431230 (Open Web Text)

Max Activating Token Index: 336

Text #3

Max Range: 4.5076. Min Range: -4.5076

Max Act: 4.3284. Min Act: -0.1700

Data Index: 2910692 (Open Web Text)

Max Activating Token Index: 776

Text #4

Max Range: 4.5076. Min Range: -4.5076

Max Act: 4.3391. Min Act: -0.1700

Data Index: 1524209 (Open Web Text)

Max Activating Token Index: 670

Text #5

Max Range: 4.5076. Min Range: -4.5076

Max Act: 4.3092. Min Act: -0.1700

Data Index: 562736 (Open Web Text)

Max Activating Token Index: 877

Text #6

Max Range: 4.5076. Min Range: -4.5076

Max Act: 4.2818. Min Act: -0.1700

Data Index: 4071234 (Open Web Text)

Max Activating Token Index: 782

Text #7

Max Range: 4.5076. Min Range: -4.5076

Max Act: 4.3138. Min Act: -0.1700

Data Index: 602133 (Open Web Text)

Max Activating Token Index: 703

Text #8

Max Range: 4.5076. Min Range: -4.5076

Max Act: 4.2892. Min Act: -0.1700

Data Index: 1443669 (Open Web Text)

Max Activating Token Index: 853

Text #9

Max Range: 4.5076. Min Range: -4.5076

Max Act: 4.2590. Min Act: -0.1700

Data Index: 8273893 (Open Web Text)

Max Activating Token Index: 558

Text #10

Max Range: 4.5076. Min Range: -4.5076

Max Act: 4.2544. Min Act: -0.1700

Data Index: 6040731 (Open Web Text)

Max Activating Token Index: 341

Text #11

Max Range: 4.5076. Min Range: -4.5076

Max Act: 4.2384. Min Act: -0.1700

Data Index: 3526394 (Open Web Text)

Max Activating Token Index: 345

Text #12

Max Range: 4.5076. Min Range: -4.5076

Max Act: 4.2617. Min Act: -0.1700

Data Index: 182163 (Open Web Text)

Max Activating Token Index: 850

Text #13

Max Range: 4.5076. Min Range: -4.5076

Max Act: 4.2456. Min Act: -0.1700

Data Index: 7146725 (Open Web Text)

Max Activating Token Index: 680

Text #14

Max Range: 4.5076. Min Range: -4.5076

Max Act: 4.2502. Min Act: -0.1700

Data Index: 7132007 (Open Web Text)

Max Activating Token Index: 740

Text #15

Max Range: 4.5076. Min Range: -4.5076

Max Act: 4.2715. Min Act: -0.1700

Data Index: 4291668 (Open Web Text)

Max Activating Token Index: 212

Text #16

Max Range: 4.5076. Min Range: -4.5076

Max Act: 4.2650. Min Act: -0.1700

Data Index: 7359867 (Open Web Text)

Max Activating Token Index: 806

Text #17

Max Range: 4.5076. Min Range: -4.5076

Max Act: 4.2646. Min Act: -0.1700

Data Index: 2833420 (Open Web Text)

Max Activating Token Index: 881

Text #18

Max Range: 4.5076. Min Range: -4.5076

Max Act: 4.2412. Min Act: -0.1700

Data Index: 4751201 (Open Web Text)

Max Activating Token Index: 1017

Text #19

Max Range: 4.5076. Min Range: -4.5076

Max Act: 4.2279. Min Act: -0.1700

Data Index: 2633861 (Open Web Text)

Max Activating Token Index: 667