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

Dataset: Open Web Text

Neuron 2901 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: 1.6454. Min Range: -1.6454

Max Act: 1.6405. Min Act: -0.1698

Data Index: 1386925 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 1.6454. Min Range: -1.6454

Max Act: 1.6454. Min Act: -0.1700

Data Index: 674467 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 1.6454. Min Range: -1.6454

Max Act: 1.6375. Min Act: -0.1700

Data Index: 8795171 (Open Web Text)

Max Activating Token Index: 298

Text #3

Max Range: 1.6454. Min Range: -1.6454

Max Act: 1.6180. Min Act: -0.1686

Data Index: 3074849 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 1.6454. Min Range: -1.6454

Max Act: 1.6157. Min Act: -0.1698

Data Index: 1189490 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 1.6454. Min Range: -1.6454

Max Act: 1.6114. Min Act: -0.1677

Data Index: 8499675 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 1.6454. Min Range: -1.6454

Max Act: 1.6020. Min Act: -0.1699

Data Index: 1474821 (Open Web Text)

Max Activating Token Index: 700

Text #7

Max Range: 1.6454. Min Range: -1.6454

Max Act: 1.5998. Min Act: -0.1700

Data Index: 308787 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 1.6454. Min Range: -1.6454

Max Act: 1.5925. Min Act: -0.1700

Data Index: 7804253 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 1.6454. Min Range: -1.6454

Max Act: 1.5919. Min Act: -0.1700

Data Index: 169669 (Open Web Text)

Max Activating Token Index: 11

Text #10

Max Range: 1.6454. Min Range: -1.6454

Max Act: 1.5929. Min Act: -0.1697

Data Index: 1210151 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 1.6454. Min Range: -1.6454

Max Act: 1.5954. Min Act: -0.1700

Data Index: 10330 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 1.6454. Min Range: -1.6454

Max Act: 1.5793. Min Act: -0.1700

Data Index: 8745124 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 1.6454. Min Range: -1.6454

Max Act: 1.5794. Min Act: -0.1700

Data Index: 337537 (Open Web Text)

Max Activating Token Index: 80

Text #14

Max Range: 1.6454. Min Range: -1.6454

Max Act: 1.5840. Min Act: -0.1700

Data Index: 3379748 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 1.6454. Min Range: -1.6454

Max Act: 1.5820. Min Act: -0.1696

Data Index: 3884182 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 1.6454. Min Range: -1.6454

Max Act: 1.5816. Min Act: -0.1700

Data Index: 4262977 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 1.6454. Min Range: -1.6454

Max Act: 1.5701. Min Act: -0.1700

Data Index: 1796045 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 1.6454. Min Range: -1.6454

Max Act: 1.5824. Min Act: -0.1700

Data Index: 7270905 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 1.6454. Min Range: -1.6454

Max Act: 1.5727. Min Act: -0.1699

Data Index: 89808 (Open Web Text)

Max Activating Token Index: 3