Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3531 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3948. Min Range: -6.3948
Max Act: 6.3948. Min Act: -0.1700
Data Index: 4774143 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3948. Min Range: -6.3948
Max Act: 6.1761. Min Act: -0.1700
Data Index: 2745949 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3948. Min Range: -6.3948
Max Act: 6.0198. Min Act: -0.1700
Data Index: 4774133 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3948. Min Range: -6.3948
Max Act: 6.0198. Min Act: -0.1699
Data Index: 6480342 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.9886. Min Act: -0.1700
Data Index: 4774141 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.9573. Min Act: -0.1700
Data Index: 4548497 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.8948. Min Act: -0.1700
Data Index: 1760762 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.9261. Min Act: -0.1700
Data Index: 1151753 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.9261. Min Act: -0.1700
Data Index: 698674 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.9261. Min Act: -0.1700
Data Index: 2550056 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.8948. Min Act: -0.1698
Data Index: 938035 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.8948. Min Act: -0.1700
Data Index: 7745337 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.8948. Min Act: -0.1700
Data Index: 5897368 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.8948. Min Act: -0.1700
Data Index: 612737 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.8636. Min Act: -0.1700
Data Index: 3935682 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.8636. Min Act: -0.1700
Data Index: 6352525 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.8636. Min Act: -0.1700
Data Index: 2550055 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.8636. Min Act: -0.1700
Data Index: 6479319 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.8636. Min Act: -0.1700
Data Index: 4419182 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3948. Min Range: -6.3948
Max Act: 5.8636. Min Act: -0.1700
Data Index: 5494043 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19