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

Dataset: Open Web Text

Neuron 203 in Layer 5

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: 3.8668. Min Range: -3.8668

Max Act: 3.8668. Min Act: -0.1700

Data Index: 1820692 (Open Web Text)

Max Activating Token Index: 113

Text #1

Max Range: 3.8668. Min Range: -3.8668

Max Act: 3.7937. Min Act: -0.1700

Data Index: 8217765 (Open Web Text)

Max Activating Token Index: 151

Text #2

Max Range: 3.8668. Min Range: -3.8668

Max Act: 3.7982. Min Act: -0.1700

Data Index: 3758758 (Open Web Text)

Max Activating Token Index: 505

Text #3

Max Range: 3.8668. Min Range: -3.8668

Max Act: 3.7651. Min Act: -0.1700

Data Index: 4671693 (Open Web Text)

Max Activating Token Index: 668

Text #4

Max Range: 3.8668. Min Range: -3.8668

Max Act: 3.7561. Min Act: -0.1700

Data Index: 2021109 (Open Web Text)

Max Activating Token Index: 517

Text #5

Max Range: 3.8668. Min Range: -3.8668

Max Act: 3.7355. Min Act: -0.1700

Data Index: 6686856 (Open Web Text)

Max Activating Token Index: 291

Text #6

Max Range: 3.8668. Min Range: -3.8668

Max Act: 3.7068. Min Act: -0.1700

Data Index: 1466959 (Open Web Text)

Max Activating Token Index: 213

Text #7

Max Range: 3.8668. Min Range: -3.8668

Max Act: 3.7154. Min Act: -0.1700

Data Index: 826423 (Open Web Text)

Max Activating Token Index: 821

Text #8

Max Range: 3.8668. Min Range: -3.8668

Max Act: 3.6921. Min Act: -0.1700

Data Index: 2745031 (Open Web Text)

Max Activating Token Index: 759

Text #9

Max Range: 3.8668. Min Range: -3.8668

Max Act: 3.6711. Min Act: -0.1700

Data Index: 7892035 (Open Web Text)

Max Activating Token Index: 386

Text #10

Max Range: 3.8668. Min Range: -3.8668

Max Act: 3.6712. Min Act: -0.1700

Data Index: 5807678 (Open Web Text)

Max Activating Token Index: 488

Text #11

Max Range: 3.8668. Min Range: -3.8668

Max Act: 3.6576. Min Act: -0.1700

Data Index: 1814521 (Open Web Text)

Max Activating Token Index: 368

Text #12

Max Range: 3.8668. Min Range: -3.8668

Max Act: 3.6678. Min Act: -0.1700

Data Index: 4498831 (Open Web Text)

Max Activating Token Index: 103

Text #13

Max Range: 3.8668. Min Range: -3.8668

Max Act: 3.6572. Min Act: -0.1700

Data Index: 4041727 (Open Web Text)

Max Activating Token Index: 456

Text #14

Max Range: 3.8668. Min Range: -3.8668

Max Act: 3.6442. Min Act: -0.1700

Data Index: 6479672 (Open Web Text)

Max Activating Token Index: 806

Text #15

Max Range: 3.8668. Min Range: -3.8668

Max Act: 3.6457. Min Act: -0.1700

Data Index: 5056703 (Open Web Text)

Max Activating Token Index: 810

Text #16

Max Range: 3.8668. Min Range: -3.8668

Max Act: 3.6597. Min Act: -0.1700

Data Index: 7066769 (Open Web Text)

Max Activating Token Index: 170

Text #17

Max Range: 3.8668. Min Range: -3.8668

Max Act: 3.6298. Min Act: -0.1700

Data Index: 2030326 (Open Web Text)

Max Activating Token Index: 943

Text #18

Max Range: 3.8668. Min Range: -3.8668

Max Act: 3.6396. Min Act: -0.1700

Data Index: 4206327 (Open Web Text)

Max Activating Token Index: 27

Text #19

Max Range: 3.8668. Min Range: -3.8668

Max Act: 3.6293. Min Act: -0.1700

Data Index: 3401183 (Open Web Text)

Max Activating Token Index: 102