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

Dataset: Open Web Text

Neuron 533 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: 4.8449. Min Range: -4.8449

Max Act: 4.8449. Min Act: -0.1700

Data Index: 7719717 (Open Web Text)

Max Activating Token Index: 542

Text #1

Max Range: 4.8449. Min Range: -4.8449

Max Act: 4.7208. Min Act: -0.1700

Data Index: 1345335 (Open Web Text)

Max Activating Token Index: 308

Text #2

Max Range: 4.8449. Min Range: -4.8449

Max Act: 4.7074. Min Act: -0.1700

Data Index: 4911979 (Open Web Text)

Max Activating Token Index: 306

Text #3

Max Range: 4.8449. Min Range: -4.8449

Max Act: 4.6357. Min Act: -0.1700

Data Index: 5249823 (Open Web Text)

Max Activating Token Index: 174

Text #4

Max Range: 4.8449. Min Range: -4.8449

Max Act: 4.6436. Min Act: -0.1700

Data Index: 7505906 (Open Web Text)

Max Activating Token Index: 209

Text #5

Max Range: 4.8449. Min Range: -4.8449

Max Act: 4.6216. Min Act: -0.1700

Data Index: 2273118 (Open Web Text)

Max Activating Token Index: 344

Text #6

Max Range: 4.8449. Min Range: -4.8449

Max Act: 4.6414. Min Act: -0.1700

Data Index: 2744747 (Open Web Text)

Max Activating Token Index: 592

Text #7

Max Range: 4.8449. Min Range: -4.8449

Max Act: 4.6392. Min Act: -0.1700

Data Index: 5820765 (Open Web Text)

Max Activating Token Index: 493

Text #8

Max Range: 4.8449. Min Range: -4.8449

Max Act: 4.6373. Min Act: -0.1700

Data Index: 6957628 (Open Web Text)

Max Activating Token Index: 459

Text #9

Max Range: 4.8449. Min Range: -4.8449

Max Act: 4.6435. Min Act: -0.1700

Data Index: 3506653 (Open Web Text)

Max Activating Token Index: 531

Text #10

Max Range: 4.8449. Min Range: -4.8449

Max Act: 4.5911. Min Act: -0.1700

Data Index: 3307878 (Open Web Text)

Max Activating Token Index: 29

Text #11

Max Range: 4.8449. Min Range: -4.8449

Max Act: 4.6036. Min Act: -0.1700

Data Index: 7237762 (Open Web Text)

Max Activating Token Index: 173

Text #12

Max Range: 4.8449. Min Range: -4.8449

Max Act: 4.6064. Min Act: -0.1700

Data Index: 2123112 (Open Web Text)

Max Activating Token Index: 113

Text #13

Max Range: 4.8449. Min Range: -4.8449

Max Act: 4.5966. Min Act: -0.1700

Data Index: 5109540 (Open Web Text)

Max Activating Token Index: 20

Text #14

Max Range: 4.8449. Min Range: -4.8449

Max Act: 4.5971. Min Act: -0.1700

Data Index: 3394082 (Open Web Text)

Max Activating Token Index: 594

Text #15

Max Range: 4.8449. Min Range: -4.8449

Max Act: 4.6060. Min Act: -0.1700

Data Index: 5855370 (Open Web Text)

Max Activating Token Index: 38

Text #16

Max Range: 4.8449. Min Range: -4.8449

Max Act: 4.6197. Min Act: -0.1700

Data Index: 2532019 (Open Web Text)

Max Activating Token Index: 423

Text #17

Max Range: 4.8449. Min Range: -4.8449

Max Act: 4.6017. Min Act: -0.1700

Data Index: 4158528 (Open Web Text)

Max Activating Token Index: 349

Text #18

Max Range: 4.8449. Min Range: -4.8449

Max Act: 4.6121. Min Act: -0.1700

Data Index: 5564408 (Open Web Text)

Max Activating Token Index: 47

Text #19

Max Range: 4.8449. Min Range: -4.8449

Max Act: 4.5973. Min Act: -0.1700

Data Index: 312914 (Open Web Text)

Max Activating Token Index: 106