Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4085 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1662. Min Range: -3.1662
Max Act: 3.1662. Min Act: -0.1700
Data Index: 5240717 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1662. Min Range: -3.1662
Max Act: 3.1347. Min Act: -0.1700
Data Index: 627430 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1662. Min Range: -3.1662
Max Act: 3.1347. Min Act: -0.1700
Data Index: 4986804 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1662. Min Range: -3.1662
Max Act: 3.0717. Min Act: -0.1700
Data Index: 952851 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1662. Min Range: -3.1662
Max Act: 3.0717. Min Act: -0.1700
Data Index: 4635275 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1662. Min Range: -3.1662
Max Act: 3.0401. Min Act: -0.1700
Data Index: 8681908 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1662. Min Range: -3.1662
Max Act: 3.0559. Min Act: -0.1700
Data Index: 8809697 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1662. Min Range: -3.1662
Max Act: 3.0243. Min Act: -0.1700
Data Index: 7265098 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1662. Min Range: -3.1662
Max Act: 3.0243. Min Act: -0.1700
Data Index: 8622104 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1662. Min Range: -3.1662
Max Act: 3.0243. Min Act: -0.1700
Data Index: 3471856 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1662. Min Range: -3.1662
Max Act: 3.0243. Min Act: -0.1700
Data Index: 3863200 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1662. Min Range: -3.1662
Max Act: 2.9927. Min Act: -0.1700
Data Index: 4437599 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1662. Min Range: -3.1662
Max Act: 2.9927. Min Act: -0.1700
Data Index: 8553913 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1662. Min Range: -3.1662
Max Act: 3.0086. Min Act: -0.1700
Data Index: 739880 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1662. Min Range: -3.1662
Max Act: 2.9927. Min Act: -0.1700
Data Index: 8622105 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1662. Min Range: -3.1662
Max Act: 2.9769. Min Act: -0.1700
Data Index: 2182863 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1662. Min Range: -3.1662
Max Act: 2.9927. Min Act: -0.1700
Data Index: 8213270 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1662. Min Range: -3.1662
Max Act: 2.9769. Min Act: -0.1700
Data Index: 7148722 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1662. Min Range: -3.1662
Max Act: 2.9769. Min Act: -0.1700
Data Index: 7637820 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1662. Min Range: -3.1662
Max Act: 2.9769. Min Act: -0.1700
Data Index: 1300932 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19