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

Dataset: Open Web Text

Neuron 228 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: 4.9521. Min Range: -4.9521

Max Act: 4.9521. Min Act: -0.1700

Data Index: 460807 (Open Web Text)

Max Activating Token Index: 49

Text #1

Max Range: 4.9521. Min Range: -4.9521

Max Act: 4.5932. Min Act: -0.1700

Data Index: 8269752 (Open Web Text)

Max Activating Token Index: 876

Text #2

Max Range: 4.9521. Min Range: -4.9521

Max Act: 4.5532. Min Act: -0.1700

Data Index: 5622047 (Open Web Text)

Max Activating Token Index: 775

Text #3

Max Range: 4.9521. Min Range: -4.9521

Max Act: 4.5594. Min Act: -0.1700

Data Index: 4492483 (Open Web Text)

Max Activating Token Index: 868

Text #4

Max Range: 4.9521. Min Range: -4.9521

Max Act: 4.5162. Min Act: -0.1700

Data Index: 3236022 (Open Web Text)

Max Activating Token Index: 965

Text #5

Max Range: 4.9521. Min Range: -4.9521

Max Act: 4.4895. Min Act: -0.1700

Data Index: 6453281 (Open Web Text)

Max Activating Token Index: 57

Text #6

Max Range: 4.9521. Min Range: -4.9521

Max Act: 4.4852. Min Act: -0.1700

Data Index: 3590252 (Open Web Text)

Max Activating Token Index: 780

Text #7

Max Range: 4.9521. Min Range: -4.9521

Max Act: 4.4946. Min Act: -0.1700

Data Index: 4718262 (Open Web Text)

Max Activating Token Index: 936

Text #8

Max Range: 4.9521. Min Range: -4.9521

Max Act: 4.4637. Min Act: -0.1700

Data Index: 2031168 (Open Web Text)

Max Activating Token Index: 245

Text #9

Max Range: 4.9521. Min Range: -4.9521

Max Act: 4.4189. Min Act: -0.1700

Data Index: 8087508 (Open Web Text)

Max Activating Token Index: 452

Text #10

Max Range: 4.9521. Min Range: -4.9521

Max Act: 4.4468. Min Act: -0.1700

Data Index: 3913452 (Open Web Text)

Max Activating Token Index: 737

Text #11

Max Range: 4.9521. Min Range: -4.9521

Max Act: 4.4750. Min Act: -0.1700

Data Index: 8263206 (Open Web Text)

Max Activating Token Index: 612

Text #12

Max Range: 4.9521. Min Range: -4.9521

Max Act: 4.4543. Min Act: -0.1700

Data Index: 6046056 (Open Web Text)

Max Activating Token Index: 110

Text #13

Max Range: 4.9521. Min Range: -4.9521

Max Act: 4.4425. Min Act: -0.1700

Data Index: 1505472 (Open Web Text)

Max Activating Token Index: 758

Text #14

Max Range: 4.9521. Min Range: -4.9521

Max Act: 4.4684. Min Act: -0.1700

Data Index: 385444 (Open Web Text)

Max Activating Token Index: 985

Text #15

Max Range: 4.9521. Min Range: -4.9521

Max Act: 4.4120. Min Act: -0.1700

Data Index: 604940 (Open Web Text)

Max Activating Token Index: 54

Text #16

Max Range: 4.9521. Min Range: -4.9521

Max Act: 4.4539. Min Act: -0.1700

Data Index: 7917429 (Open Web Text)

Max Activating Token Index: 402

Text #17

Max Range: 4.9521. Min Range: -4.9521

Max Act: 4.4409. Min Act: -0.1700

Data Index: 507423 (Open Web Text)

Max Activating Token Index: 927

Text #18

Max Range: 4.9521. Min Range: -4.9521

Max Act: 4.4391. Min Act: -0.1700

Data Index: 5798702 (Open Web Text)

Max Activating Token Index: 796

Text #19

Max Range: 4.9521. Min Range: -4.9521

Max Act: 4.4574. Min Act: -0.1700

Data Index: 350357 (Open Web Text)

Max Activating Token Index: 582