Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6054 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4573. Min Range: -7.4573
Max Act: 7.4573. Min Act: -0.1700
Data Index: 7722151 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4573. Min Range: -7.4573
Max Act: 7.3636. Min Act: -0.1700
Data Index: 6691452 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4573. Min Range: -7.4573
Max Act: 7.3323. Min Act: -0.1700
Data Index: 3380606 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4573. Min Range: -7.4573
Max Act: 7.2698. Min Act: -0.1700
Data Index: 4063265 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4573. Min Range: -7.4573
Max Act: 7.1448. Min Act: -0.1700
Data Index: 69216 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4573. Min Range: -7.4573
Max Act: 7.0823. Min Act: -0.1700
Data Index: 5133266 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4573. Min Range: -7.4573
Max Act: 7.0823. Min Act: -0.1700
Data Index: 2005660 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4573. Min Range: -7.4573
Max Act: 7.0511. Min Act: -0.1700
Data Index: 6424704 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4573. Min Range: -7.4573
Max Act: 7.0198. Min Act: -0.1700
Data Index: 8358315 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4573. Min Range: -7.4573
Max Act: 6.9886. Min Act: -0.1700
Data Index: 4660883 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4573. Min Range: -7.4573
Max Act: 6.9886. Min Act: -0.1700
Data Index: 6726159 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4573. Min Range: -7.4573
Max Act: 6.9573. Min Act: -0.1700
Data Index: 4165880 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4573. Min Range: -7.4573
Max Act: 6.9261. Min Act: -0.1700
Data Index: 7830326 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4573. Min Range: -7.4573
Max Act: 6.9573. Min Act: -0.1700
Data Index: 8577962 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4573. Min Range: -7.4573
Max Act: 6.9573. Min Act: -0.1700
Data Index: 1104342 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4573. Min Range: -7.4573
Max Act: 6.9261. Min Act: -0.1700
Data Index: 1093326 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4573. Min Range: -7.4573
Max Act: 6.9261. Min Act: -0.1700
Data Index: 7895594 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4573. Min Range: -7.4573
Max Act: 6.9261. Min Act: -0.1700
Data Index: 2742427 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4573. Min Range: -7.4573
Max Act: 6.9261. Min Act: -0.1700
Data Index: 4896484 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4573. Min Range: -7.4573
Max Act: 6.8948. Min Act: -0.1700
Data Index: 5286756 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #19