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

Dataset: Open Web Text

Neuron 1825 in Layer 1

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: 7.2677. Min Range: -7.2677

Max Act: 7.2677. Min Act: -0.1700

Data Index: 7458734 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 7.2677. Min Range: -7.2677

Max Act: 7.2476. Min Act: -0.1700

Data Index: 5707468 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 7.2677. Min Range: -7.2677

Max Act: 7.1908. Min Act: -0.1700

Data Index: 863829 (Open Web Text)

Max Activating Token Index: 10

Text #3

Max Range: 7.2677. Min Range: -7.2677

Max Act: 7.1948. Min Act: -0.1700

Data Index: 4806220 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 7.2677. Min Range: -7.2677

Max Act: 7.1934. Min Act: -0.1700

Data Index: 2200417 (Open Web Text)

Max Activating Token Index: 45

Text #5

Max Range: 7.2677. Min Range: -7.2677

Max Act: 7.2055. Min Act: -0.1700

Data Index: 5356712 (Open Web Text)

Max Activating Token Index: 15

Text #6

Max Range: 7.2677. Min Range: -7.2677

Max Act: 7.1976. Min Act: -0.1700

Data Index: 642221 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 7.2677. Min Range: -7.2677

Max Act: 7.1715. Min Act: -0.1700

Data Index: 5950864 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 7.2677. Min Range: -7.2677

Max Act: 7.1742. Min Act: -0.1700

Data Index: 1027157 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 7.2677. Min Range: -7.2677

Max Act: 7.1447. Min Act: -0.1700

Data Index: 999400 (Open Web Text)

Max Activating Token Index: 336

Text #10

Max Range: 7.2677. Min Range: -7.2677

Max Act: 7.1567. Min Act: -0.1700

Data Index: 4407173 (Open Web Text)

Max Activating Token Index: 34

Text #11

Max Range: 7.2677. Min Range: -7.2677

Max Act: 7.1244. Min Act: -0.1699

Data Index: 368245 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 7.2677. Min Range: -7.2677

Max Act: 7.1290. Min Act: -0.1700

Data Index: 5237733 (Open Web Text)

Max Activating Token Index: 49

Text #13

Max Range: 7.2677. Min Range: -7.2677

Max Act: 7.1215. Min Act: -0.1700

Data Index: 6731112 (Open Web Text)

Max Activating Token Index: 33

Text #14

Max Range: 7.2677. Min Range: -7.2677

Max Act: 7.1167. Min Act: -0.1700

Data Index: 8510512 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 7.2677. Min Range: -7.2677

Max Act: 7.1416. Min Act: -0.1700

Data Index: 2765988 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 7.2677. Min Range: -7.2677

Max Act: 7.1606. Min Act: -0.1700

Data Index: 1167354 (Open Web Text)

Max Activating Token Index: 42

Text #17

Max Range: 7.2677. Min Range: -7.2677

Max Act: 7.1099. Min Act: -0.1700

Data Index: 6399073 (Open Web Text)

Max Activating Token Index: 24

Text #18

Max Range: 7.2677. Min Range: -7.2677

Max Act: 7.0961. Min Act: -0.1700

Data Index: 2872605 (Open Web Text)

Max Activating Token Index: 37

Text #19

Max Range: 7.2677. Min Range: -7.2677

Max Act: 7.0787. Min Act: -0.1700

Data Index: 7300736 (Open Web Text)

Max Activating Token Index: 8