Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2022 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 6.1029. Min Range: -6.1029
Max Act: 6.1029. Min Act: -0.1700
Data Index: 5474810 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1029. Min Range: -6.1029
Max Act: 5.7904. Min Act: -0.1700
Data Index: 5629860 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1029. Min Range: -6.1029
Max Act: 5.6654. Min Act: -0.1700
Data Index: 6183963 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1029. Min Range: -6.1029
Max Act: 5.6654. Min Act: -0.1700
Data Index: 8723427 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1029. Min Range: -6.1029
Max Act: 5.6342. Min Act: -0.1700
Data Index: 40667 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1029. Min Range: -6.1029
Max Act: 5.6654. Min Act: -0.1700
Data Index: 704810 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1029. Min Range: -6.1029
Max Act: 5.6342. Min Act: -0.1700
Data Index: 1596725 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1029. Min Range: -6.1029
Max Act: 5.6342. Min Act: -0.1700
Data Index: 5474815 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1029. Min Range: -6.1029
Max Act: 5.6029. Min Act: -0.1700
Data Index: 6548971 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1029. Min Range: -6.1029
Max Act: 5.5717. Min Act: -0.1700
Data Index: 5474808 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1029. Min Range: -6.1029
Max Act: 5.5717. Min Act: -0.1700
Data Index: 6244148 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1029. Min Range: -6.1029
Max Act: 5.5092. Min Act: -0.1700
Data Index: 8634570 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1029. Min Range: -6.1029
Max Act: 5.4467. Min Act: -0.1700
Data Index: 7961852 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1029. Min Range: -6.1029
Max Act: 5.4154. Min Act: -0.1700
Data Index: 6321080 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1029. Min Range: -6.1029
Max Act: 5.4154. Min Act: -0.1700
Data Index: 2981287 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1029. Min Range: -6.1029
Max Act: 5.4154. Min Act: -0.1700
Data Index: 5474848 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1029. Min Range: -6.1029
Max Act: 5.3529. Min Act: -0.1700
Data Index: 3127289 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1029. Min Range: -6.1029
Max Act: 5.3217. Min Act: -0.1700
Data Index: 8586499 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1029. Min Range: -6.1029
Max Act: 5.3217. Min Act: -0.1700
Data Index: 4925967 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1029. Min Range: -6.1029
Max Act: 5.3529. Min Act: -0.1700
Data Index: 5474849 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19