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

Dataset: Open Web Text

Neuron 158 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: 1.1659. Min Range: -1.1659

Max Act: 1.1659. Min Act: -0.1686

Data Index: 2941900 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.1659. Min Range: -1.1659

Max Act: 1.1622. Min Act: -0.1686

Data Index: 4650493 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 1.1659. Min Range: -1.1659

Max Act: 1.1481. Min Act: -0.1686

Data Index: 5734600 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 1.1659. Min Range: -1.1659

Max Act: 1.1384. Min Act: -0.1686

Data Index: 4708788 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.1659. Min Range: -1.1659

Max Act: 1.1331. Min Act: -0.1686

Data Index: 2985498 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 1.1659. Min Range: -1.1659

Max Act: 1.1260. Min Act: -0.1686

Data Index: 8703514 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 1.1659. Min Range: -1.1659

Max Act: 1.1326. Min Act: -0.1686

Data Index: 6317139 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 1.1659. Min Range: -1.1659

Max Act: 1.1366. Min Act: -0.1686

Data Index: 8722329 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 1.1659. Min Range: -1.1659

Max Act: 1.1048. Min Act: -0.1686

Data Index: 4561603 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 1.1659. Min Range: -1.1659

Max Act: 1.1076. Min Act: -0.1686

Data Index: 5315860 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 1.1659. Min Range: -1.1659

Max Act: 1.1099. Min Act: -0.1686

Data Index: 7985505 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 1.1659. Min Range: -1.1659

Max Act: 1.1139. Min Act: -0.1686

Data Index: 1421669 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 1.1659. Min Range: -1.1659

Max Act: 1.1123. Min Act: -0.1686

Data Index: 2101363 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 1.1659. Min Range: -1.1659

Max Act: 1.0949. Min Act: -0.1686

Data Index: 1190306 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 1.1659. Min Range: -1.1659

Max Act: 1.0973. Min Act: -0.1686

Data Index: 6668855 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 1.1659. Min Range: -1.1659

Max Act: 1.1005. Min Act: -0.1686

Data Index: 7244305 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 1.1659. Min Range: -1.1659

Max Act: 1.0963. Min Act: -0.1686

Data Index: 2885082 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 1.1659. Min Range: -1.1659

Max Act: 1.1050. Min Act: -0.1686

Data Index: 1079838 (Open Web Text)

Max Activating Token Index: 630

Text #18

Max Range: 1.1659. Min Range: -1.1659

Max Act: 1.0937. Min Act: -0.1686

Data Index: 101286 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 1.1659. Min Range: -1.1659

Max Act: 1.0885. Min Act: -0.1686

Data Index: 8313152 (Open Web Text)

Max Activating Token Index: 1023