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

Dataset: Open Web Text

Neuron 1115 in Layer 2

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: 4.1390. Min Range: -4.1390

Max Act: 4.1390. Min Act: -0.1700

Data Index: 6039208 (Open Web Text)

Max Activating Token Index: 202

Text #1

Max Range: 4.1390. Min Range: -4.1390

Max Act: 4.0743. Min Act: -0.1700

Data Index: 3400340 (Open Web Text)

Max Activating Token Index: 341

Text #2

Max Range: 4.1390. Min Range: -4.1390

Max Act: 4.1285. Min Act: -0.1700

Data Index: 1267950 (Open Web Text)

Max Activating Token Index: 449

Text #3

Max Range: 4.1390. Min Range: -4.1390

Max Act: 4.1164. Min Act: -0.1700

Data Index: 6147641 (Open Web Text)

Max Activating Token Index: 502

Text #4

Max Range: 4.1390. Min Range: -4.1390

Max Act: 4.0776. Min Act: -0.1700

Data Index: 6460912 (Open Web Text)

Max Activating Token Index: 91

Text #5

Max Range: 4.1390. Min Range: -4.1390

Max Act: 4.0543. Min Act: -0.1700

Data Index: 8231297 (Open Web Text)

Max Activating Token Index: 355

Text #6

Max Range: 4.1390. Min Range: -4.1390

Max Act: 4.0320. Min Act: -0.1700

Data Index: 6600932 (Open Web Text)

Max Activating Token Index: 75

Text #7

Max Range: 4.1390. Min Range: -4.1390

Max Act: 4.0466. Min Act: -0.1700

Data Index: 5083919 (Open Web Text)

Max Activating Token Index: 545

Text #8

Max Range: 4.1390. Min Range: -4.1390

Max Act: 4.0102. Min Act: -0.1700

Data Index: 2824168 (Open Web Text)

Max Activating Token Index: 529

Text #9

Max Range: 4.1390. Min Range: -4.1390

Max Act: 3.9749. Min Act: -0.1700

Data Index: 6156094 (Open Web Text)

Max Activating Token Index: 59

Text #10

Max Range: 4.1390. Min Range: -4.1390

Max Act: 3.9909. Min Act: -0.1700

Data Index: 889801 (Open Web Text)

Max Activating Token Index: 915

Text #11

Max Range: 4.1390. Min Range: -4.1390

Max Act: 3.9932. Min Act: -0.1700

Data Index: 2548622 (Open Web Text)

Max Activating Token Index: 73

Text #12

Max Range: 4.1390. Min Range: -4.1390

Max Act: 3.9706. Min Act: -0.1700

Data Index: 910226 (Open Web Text)

Max Activating Token Index: 531

Text #13

Max Range: 4.1390. Min Range: -4.1390

Max Act: 3.9629. Min Act: -0.1700

Data Index: 5238752 (Open Web Text)

Max Activating Token Index: 754

Text #14

Max Range: 4.1390. Min Range: -4.1390

Max Act: 3.9211. Min Act: -0.1700

Data Index: 4955047 (Open Web Text)

Max Activating Token Index: 815

Text #15

Max Range: 4.1390. Min Range: -4.1390

Max Act: 3.9192. Min Act: -0.1700

Data Index: 2829755 (Open Web Text)

Max Activating Token Index: 442

Text #16

Max Range: 4.1390. Min Range: -4.1390

Max Act: 3.8895. Min Act: -0.1700

Data Index: 7974692 (Open Web Text)

Max Activating Token Index: 1008

Text #17

Max Range: 4.1390. Min Range: -4.1390

Max Act: 3.9179. Min Act: -0.1700

Data Index: 7858574 (Open Web Text)

Max Activating Token Index: 783

Text #18

Max Range: 4.1390. Min Range: -4.1390

Max Act: 3.9223. Min Act: -0.1700

Data Index: 5680044 (Open Web Text)

Max Activating Token Index: 650

Text #19

Max Range: 4.1390. Min Range: -4.1390

Max Act: 3.9246. Min Act: -0.1700

Data Index: 238636 (Open Web Text)

Max Activating Token Index: 53