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

Dataset: Open Web Text

Neuron 1541 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: 6.3378. Min Range: -6.3378

Max Act: 6.3378. Min Act: -0.1700

Data Index: 5429362 (Open Web Text)

Max Activating Token Index: 14

Text #1

Max Range: 6.3378. Min Range: -6.3378

Max Act: 6.2359. Min Act: -0.1700

Data Index: 5070263 (Open Web Text)

Max Activating Token Index: 14

Text #2

Max Range: 6.3378. Min Range: -6.3378

Max Act: 6.1622. Min Act: -0.1700

Data Index: 4859734 (Open Web Text)

Max Activating Token Index: 848

Text #3

Max Range: 6.3378. Min Range: -6.3378

Max Act: 6.1572. Min Act: -0.1700

Data Index: 5687394 (Open Web Text)

Max Activating Token Index: 998

Text #4

Max Range: 6.3378. Min Range: -6.3378

Max Act: 6.1228. Min Act: -0.1700

Data Index: 2137768 (Open Web Text)

Max Activating Token Index: 545

Text #5

Max Range: 6.3378. Min Range: -6.3378

Max Act: 6.1214. Min Act: -0.1700

Data Index: 987058 (Open Web Text)

Max Activating Token Index: 1010

Text #6

Max Range: 6.3378. Min Range: -6.3378

Max Act: 6.1186. Min Act: -0.1700

Data Index: 5285720 (Open Web Text)

Max Activating Token Index: 303

Text #7

Max Range: 6.3378. Min Range: -6.3378

Max Act: 6.0990. Min Act: -0.1700

Data Index: 3772406 (Open Web Text)

Max Activating Token Index: 14

Text #8

Max Range: 6.3378. Min Range: -6.3378

Max Act: 6.1026. Min Act: -0.1700

Data Index: 5574972 (Open Web Text)

Max Activating Token Index: 795

Text #9

Max Range: 6.3378. Min Range: -6.3378

Max Act: 6.0910. Min Act: -0.1700

Data Index: 6900724 (Open Web Text)

Max Activating Token Index: 20

Text #10

Max Range: 6.3378. Min Range: -6.3378

Max Act: 6.0458. Min Act: -0.1700

Data Index: 250399 (Open Web Text)

Max Activating Token Index: 774

Text #11

Max Range: 6.3378. Min Range: -6.3378

Max Act: 6.0470. Min Act: -0.1700

Data Index: 6755564 (Open Web Text)

Max Activating Token Index: 748

Text #12

Max Range: 6.3378. Min Range: -6.3378

Max Act: 6.0522. Min Act: -0.1700

Data Index: 5279285 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 6.3378. Min Range: -6.3378

Max Act: 6.0236. Min Act: -0.1700

Data Index: 7555908 (Open Web Text)

Max Activating Token Index: 659

Text #14

Max Range: 6.3378. Min Range: -6.3378

Max Act: 5.9261. Min Act: -0.1700

Data Index: 8554085 (Open Web Text)

Max Activating Token Index: 972

Text #15

Max Range: 6.3378. Min Range: -6.3378

Max Act: 5.9949. Min Act: -0.1700

Data Index: 2757322 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 6.3378. Min Range: -6.3378

Max Act: 5.9962. Min Act: -0.1700

Data Index: 6229221 (Open Web Text)

Max Activating Token Index: 422

Text #17

Max Range: 6.3378. Min Range: -6.3378

Max Act: 5.9687. Min Act: -0.1700

Data Index: 7511274 (Open Web Text)

Max Activating Token Index: 863

Text #18

Max Range: 6.3378. Min Range: -6.3378

Max Act: 5.9974. Min Act: -0.1700

Data Index: 5230785 (Open Web Text)

Max Activating Token Index: 137

Text #19

Max Range: 6.3378. Min Range: -6.3378

Max Act: 5.9786. Min Act: -0.1700

Data Index: 6622233 (Open Web Text)

Max Activating Token Index: 581