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

Dataset: Open Web Text

Neuron 1577 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: 1.8723. Min Range: -1.8723

Max Act: 1.8723. Min Act: -0.1700

Data Index: 3985840 (Open Web Text)

Max Activating Token Index: 139

Text #1

Max Range: 1.8723. Min Range: -1.8723

Max Act: 1.8569. Min Act: -0.1700

Data Index: 5359932 (Open Web Text)

Max Activating Token Index: 532

Text #2

Max Range: 1.8723. Min Range: -1.8723

Max Act: 1.8434. Min Act: -0.1700

Data Index: 7953396 (Open Web Text)

Max Activating Token Index: 985

Text #3

Max Range: 1.8723. Min Range: -1.8723

Max Act: 1.8449. Min Act: -0.1700

Data Index: 1662188 (Open Web Text)

Max Activating Token Index: 552

Text #4

Max Range: 1.8723. Min Range: -1.8723

Max Act: 1.8393. Min Act: -0.1700

Data Index: 7460174 (Open Web Text)

Max Activating Token Index: 16

Text #5

Max Range: 1.8723. Min Range: -1.8723

Max Act: 1.8221. Min Act: -0.1700

Data Index: 741153 (Open Web Text)

Max Activating Token Index: 919

Text #6

Max Range: 1.8723. Min Range: -1.8723

Max Act: 1.8088. Min Act: -0.1700

Data Index: 1307700 (Open Web Text)

Max Activating Token Index: 512

Text #7

Max Range: 1.8723. Min Range: -1.8723

Max Act: 1.8050. Min Act: -0.1700

Data Index: 5374763 (Open Web Text)

Max Activating Token Index: 887

Text #8

Max Range: 1.8723. Min Range: -1.8723

Max Act: 1.7914. Min Act: -0.1700

Data Index: 7460173 (Open Web Text)

Max Activating Token Index: 984

Text #9

Max Range: 1.8723. Min Range: -1.8723

Max Act: 1.7886. Min Act: -0.1700

Data Index: 232371 (Open Web Text)

Max Activating Token Index: 409

Text #10

Max Range: 1.8723. Min Range: -1.8723

Max Act: 1.7889. Min Act: -0.1700

Data Index: 8741735 (Open Web Text)

Max Activating Token Index: 87

Text #11

Max Range: 1.8723. Min Range: -1.8723

Max Act: 1.7863. Min Act: -0.1700

Data Index: 2689584 (Open Web Text)

Max Activating Token Index: 584

Text #12

Max Range: 1.8723. Min Range: -1.8723

Max Act: 1.7927. Min Act: -0.1700

Data Index: 5598461 (Open Web Text)

Max Activating Token Index: 985

Text #13

Max Range: 1.8723. Min Range: -1.8723

Max Act: 1.7687. Min Act: -0.1700

Data Index: 1791858 (Open Web Text)

Max Activating Token Index: 95

Text #14

Max Range: 1.8723. Min Range: -1.8723

Max Act: 1.7681. Min Act: -0.1700

Data Index: 5689741 (Open Web Text)

Max Activating Token Index: 123

Text #15

Max Range: 1.8723. Min Range: -1.8723

Max Act: 1.7700. Min Act: -0.1700

Data Index: 6538036 (Open Web Text)

Max Activating Token Index: 459

Text #16

Max Range: 1.8723. Min Range: -1.8723

Max Act: 1.7655. Min Act: -0.1700

Data Index: 5282714 (Open Web Text)

Max Activating Token Index: 384

Text #17

Max Range: 1.8723. Min Range: -1.8723

Max Act: 1.7607. Min Act: -0.1700

Data Index: 5010269 (Open Web Text)

Max Activating Token Index: 788

Text #18

Max Range: 1.8723. Min Range: -1.8723

Max Act: 1.7525. Min Act: -0.1700

Data Index: 1262225 (Open Web Text)

Max Activating Token Index: 445

Text #19

Max Range: 1.8723. Min Range: -1.8723

Max Act: 1.7554. Min Act: -0.1700

Data Index: 5624946 (Open Web Text)

Max Activating Token Index: 368