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

Dataset: Open Web Text

Neuron 1693 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: 5.2195. Min Range: -5.2195

Max Act: 5.2195. Min Act: -0.1700

Data Index: 6632709 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 5.2195. Min Range: -5.2195

Max Act: 5.1645. Min Act: -0.1700

Data Index: 5382539 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 5.2195. Min Range: -5.2195

Max Act: 5.1568. Min Act: -0.1700

Data Index: 5014809 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 5.2195. Min Range: -5.2195

Max Act: 5.1568. Min Act: -0.1700

Data Index: 8040776 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 5.2195. Min Range: -5.2195

Max Act: 5.1568. Min Act: -0.1700

Data Index: 6768418 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 5.2195. Min Range: -5.2195

Max Act: 5.1568. Min Act: -0.1700

Data Index: 3861113 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 5.2195. Min Range: -5.2195

Max Act: 5.1568. Min Act: -0.1700

Data Index: 2158220 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 5.2195. Min Range: -5.2195

Max Act: 5.1568. Min Act: -0.1700

Data Index: 5392124 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 5.2195. Min Range: -5.2195

Max Act: 5.1501. Min Act: -0.1700

Data Index: 4348217 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 5.2195. Min Range: -5.2195

Max Act: 5.1290. Min Act: -0.1700

Data Index: 4237227 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 5.2195. Min Range: -5.2195

Max Act: 5.1329. Min Act: -0.1700

Data Index: 8311679 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 5.2195. Min Range: -5.2195

Max Act: 5.1205. Min Act: -0.1700

Data Index: 4217724 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 5.2195. Min Range: -5.2195

Max Act: 5.1188. Min Act: -0.1700

Data Index: 8155808 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 5.2195. Min Range: -5.2195

Max Act: 5.1316. Min Act: -0.1700

Data Index: 6359170 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 5.2195. Min Range: -5.2195

Max Act: 5.1202. Min Act: -0.1700

Data Index: 2199210 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 5.2195. Min Range: -5.2195

Max Act: 5.1086. Min Act: -0.1700

Data Index: 3260816 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 5.2195. Min Range: -5.2195

Max Act: 5.0948. Min Act: -0.1700

Data Index: 4603483 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 5.2195. Min Range: -5.2195

Max Act: 5.1202. Min Act: -0.1700

Data Index: 5640827 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 5.2195. Min Range: -5.2195

Max Act: 5.1202. Min Act: -0.1700

Data Index: 7721152 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 5.2195. Min Range: -5.2195

Max Act: 5.1000. Min Act: -0.1700

Data Index: 3968075 (Open Web Text)

Max Activating Token Index: 3