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

Dataset: Open Web Text

Neuron 560 in Layer 0

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: 5.7162. Min Range: -5.7162

Max Act: 5.7162. Min Act: -0.1700

Data Index: 8763942 (Open Web Text)

Max Activating Token Index: 851

Text #1

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.6831. Min Act: -0.1700

Data Index: 5584641 (Open Web Text)

Max Activating Token Index: 437

Text #2

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.6696. Min Act: -0.1700

Data Index: 1459627 (Open Web Text)

Max Activating Token Index: 67

Text #3

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.6074. Min Act: -0.1700

Data Index: 1124735 (Open Web Text)

Max Activating Token Index: 415

Text #4

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.6036. Min Act: -0.1700

Data Index: 7666857 (Open Web Text)

Max Activating Token Index: 645

Text #5

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.5411. Min Act: -0.1700

Data Index: 8013330 (Open Web Text)

Max Activating Token Index: 542

Text #6

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.5545. Min Act: -0.1700

Data Index: 5107433 (Open Web Text)

Max Activating Token Index: 831

Text #7

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.5437. Min Act: -0.1700

Data Index: 2172323 (Open Web Text)

Max Activating Token Index: 351

Text #8

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.5530. Min Act: -0.1700

Data Index: 6505175 (Open Web Text)

Max Activating Token Index: 47

Text #9

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.5536. Min Act: -0.1700

Data Index: 6890737 (Open Web Text)

Max Activating Token Index: 599

Text #10

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.5399. Min Act: -0.1700

Data Index: 2738465 (Open Web Text)

Max Activating Token Index: 515

Text #11

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.5197. Min Act: -0.1700

Data Index: 5210796 (Open Web Text)

Max Activating Token Index: 645

Text #12

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.5008. Min Act: -0.1700

Data Index: 4020625 (Open Web Text)

Max Activating Token Index: 859

Text #13

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.5166. Min Act: -0.1700

Data Index: 3184578 (Open Web Text)

Max Activating Token Index: 397

Text #14

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.5196. Min Act: -0.1700

Data Index: 989983 (Open Web Text)

Max Activating Token Index: 74

Text #15

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.4929. Min Act: -0.1700

Data Index: 372723 (Open Web Text)

Max Activating Token Index: 652

Text #16

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.4565. Min Act: -0.1700

Data Index: 615926 (Open Web Text)

Max Activating Token Index: 271

Text #17

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.4867. Min Act: -0.1700

Data Index: 1531729 (Open Web Text)

Max Activating Token Index: 560

Text #18

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.4799. Min Act: -0.1700

Data Index: 4558865 (Open Web Text)

Max Activating Token Index: 225

Text #19

Max Range: 5.7162. Min Range: -5.7162

Max Act: 5.4936. Min Act: -0.1700

Data Index: 3384951 (Open Web Text)

Max Activating Token Index: 998