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

Dataset: Open Web Text

Neuron 606 in Layer 4

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: 3.3085. Min Range: -3.3085

Max Act: 3.3085. Min Act: -0.1700

Data Index: 3377966 (Open Web Text)

Max Activating Token Index: 695

Text #1

Max Range: 3.3085. Min Range: -3.3085

Max Act: 3.2605. Min Act: -0.1700

Data Index: 3377957 (Open Web Text)

Max Activating Token Index: 1021

Text #2

Max Range: 3.3085. Min Range: -3.3085

Max Act: 3.2311. Min Act: -0.1700

Data Index: 1589486 (Open Web Text)

Max Activating Token Index: 221

Text #3

Max Range: 3.3085. Min Range: -3.3085

Max Act: 3.1996. Min Act: -0.1700

Data Index: 8134848 (Open Web Text)

Max Activating Token Index: 218

Text #4

Max Range: 3.3085. Min Range: -3.3085

Max Act: 3.1832. Min Act: -0.1700

Data Index: 1589469 (Open Web Text)

Max Activating Token Index: 218

Text #5

Max Range: 3.3085. Min Range: -3.3085

Max Act: 3.1148. Min Act: -0.1700

Data Index: 2774625 (Open Web Text)

Max Activating Token Index: 154

Text #6

Max Range: 3.3085. Min Range: -3.3085

Max Act: 3.1424. Min Act: -0.1700

Data Index: 4970893 (Open Web Text)

Max Activating Token Index: 851

Text #7

Max Range: 3.3085. Min Range: -3.3085

Max Act: 3.1523. Min Act: -0.1700

Data Index: 4970907 (Open Web Text)

Max Activating Token Index: 888

Text #8

Max Range: 3.3085. Min Range: -3.3085

Max Act: 3.1184. Min Act: -0.1700

Data Index: 5714261 (Open Web Text)

Max Activating Token Index: 794

Text #9

Max Range: 3.3085. Min Range: -3.3085

Max Act: 3.0892. Min Act: -0.1700

Data Index: 7031142 (Open Web Text)

Max Activating Token Index: 187

Text #10

Max Range: 3.3085. Min Range: -3.3085

Max Act: 3.0534. Min Act: -0.1700

Data Index: 8608013 (Open Web Text)

Max Activating Token Index: 302

Text #11

Max Range: 3.3085. Min Range: -3.3085

Max Act: 3.0820. Min Act: -0.1700

Data Index: 5714260 (Open Web Text)

Max Activating Token Index: 47

Text #12

Max Range: 3.3085. Min Range: -3.3085

Max Act: 3.0793. Min Act: -0.1700

Data Index: 2462223 (Open Web Text)

Max Activating Token Index: 95

Text #13

Max Range: 3.3085. Min Range: -3.3085

Max Act: 3.0699. Min Act: -0.1700

Data Index: 8560253 (Open Web Text)

Max Activating Token Index: 349

Text #14

Max Range: 3.3085. Min Range: -3.3085

Max Act: 3.0362. Min Act: -0.1700

Data Index: 4119330 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 3.3085. Min Range: -3.3085

Max Act: 3.0362. Min Act: -0.1700

Data Index: 7826586 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.3085. Min Range: -3.3085

Max Act: 3.0362. Min Act: -0.1700

Data Index: 5693693 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 3.3085. Min Range: -3.3085

Max Act: 3.0362. Min Act: -0.1700

Data Index: 5323712 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 3.3085. Min Range: -3.3085

Max Act: 3.0457. Min Act: -0.1700

Data Index: 1606643 (Open Web Text)

Max Activating Token Index: 78

Text #19

Max Range: 3.3085. Min Range: -3.3085

Max Act: 3.0340. Min Act: -0.1700

Data Index: 8484870 (Open Web Text)

Max Activating Token Index: 600