Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1433 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8698. Min Range: -6.8698
Max Act: 6.8698. Min Act: -0.1700
Data Index: 6300938 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8698. Min Range: -6.8698
Max Act: 6.8386. Min Act: -0.1700
Data Index: 8360671 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8698. Min Range: -6.8698
Max Act: 6.8073. Min Act: -0.1700
Data Index: 358920 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8698. Min Range: -6.8698
Max Act: 6.7136. Min Act: -0.1700
Data Index: 3000891 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8698. Min Range: -6.8698
Max Act: 6.5573. Min Act: -0.1700
Data Index: 8094332 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8698. Min Range: -6.8698
Max Act: 6.0886. Min Act: -0.1700
Data Index: 6219811 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8698. Min Range: -6.8698
Max Act: 6.1198. Min Act: -0.1700
Data Index: 4187204 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8698. Min Range: -6.8698
Max Act: 6.0573. Min Act: -0.1700
Data Index: 6314425 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8698. Min Range: -6.8698
Max Act: 6.0573. Min Act: -0.1700
Data Index: 4563088 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8698. Min Range: -6.8698
Max Act: 5.9948. Min Act: -0.1700
Data Index: 5522160 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8698. Min Range: -6.8698
Max Act: 5.9636. Min Act: -0.1700
Data Index: 8142048 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8698. Min Range: -6.8698
Max Act: 5.9948. Min Act: -0.1700
Data Index: 6219812 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8698. Min Range: -6.8698
Max Act: 5.9948. Min Act: -0.1700
Data Index: 7516408 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8698. Min Range: -6.8698
Max Act: 5.9948. Min Act: -0.1700
Data Index: 4187203 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8698. Min Range: -6.8698
Max Act: 5.9323. Min Act: -0.1700
Data Index: 6314426 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8698. Min Range: -6.8698
Max Act: 5.9323. Min Act: -0.1700
Data Index: 8387180 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8698. Min Range: -6.8698
Max Act: 5.9636. Min Act: -0.1700
Data Index: 5551054 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8698. Min Range: -6.8698
Max Act: 5.9323. Min Act: -0.1700
Data Index: 7986515 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8698. Min Range: -6.8698
Max Act: 5.9323. Min Act: -0.1700
Data Index: 8142047 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8698. Min Range: -6.8698
Max Act: 5.9636. Min Act: -0.1700
Data Index: 3003086 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19