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

Dataset: Open Web Text

Neuron 3032 in Layer 4

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: 4.9388. Min Range: -4.9388

Max Act: 4.9388. Min Act: -0.1700

Data Index: 1001798 (Open Web Text)

Max Activating Token Index: 776

Text #1

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.7291. Min Act: -0.1700

Data Index: 4189930 (Open Web Text)

Max Activating Token Index: 793

Text #2

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.6102. Min Act: -0.1700

Data Index: 7429465 (Open Web Text)

Max Activating Token Index: 944

Text #3

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.6526. Min Act: -0.1700

Data Index: 440213 (Open Web Text)

Max Activating Token Index: 741

Text #4

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.5948. Min Act: -0.1700

Data Index: 7246124 (Open Web Text)

Max Activating Token Index: 877

Text #5

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.5997. Min Act: -0.1700

Data Index: 5655898 (Open Web Text)

Max Activating Token Index: 339

Text #6

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.5876. Min Act: -0.1700

Data Index: 489397 (Open Web Text)

Max Activating Token Index: 592

Text #7

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.6119. Min Act: -0.1700

Data Index: 2143195 (Open Web Text)

Max Activating Token Index: 163

Text #8

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.5958. Min Act: -0.1700

Data Index: 3949607 (Open Web Text)

Max Activating Token Index: 662

Text #9

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.5588. Min Act: -0.1700

Data Index: 8530064 (Open Web Text)

Max Activating Token Index: 163

Text #10

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.5707. Min Act: -0.1700

Data Index: 2648301 (Open Web Text)

Max Activating Token Index: 529

Text #11

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.5535. Min Act: -0.1700

Data Index: 2890488 (Open Web Text)

Max Activating Token Index: 184

Text #12

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.5691. Min Act: -0.1700

Data Index: 2524828 (Open Web Text)

Max Activating Token Index: 852

Text #13

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.5374. Min Act: -0.1700

Data Index: 2955810 (Open Web Text)

Max Activating Token Index: 319

Text #14

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.5526. Min Act: -0.1700

Data Index: 6884981 (Open Web Text)

Max Activating Token Index: 371

Text #15

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.5391. Min Act: -0.1700

Data Index: 2932529 (Open Web Text)

Max Activating Token Index: 705

Text #16

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.5269. Min Act: -0.1700

Data Index: 7503459 (Open Web Text)

Max Activating Token Index: 164

Text #17

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.5257. Min Act: -0.1700

Data Index: 5152220 (Open Web Text)

Max Activating Token Index: 983

Text #18

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.5374. Min Act: -0.1700

Data Index: 6603485 (Open Web Text)

Max Activating Token Index: 866

Text #19

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.5383. Min Act: -0.1700

Data Index: 2481789 (Open Web Text)

Max Activating Token Index: 548