Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5206 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5692. Min Range: -8.5692
Max Act: 8.5692. Min Act: -0.1700
Data Index: 2657803 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5692. Min Range: -8.5692
Max Act: 8.1317. Min Act: -0.1700
Data Index: 4250984 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5692. Min Range: -8.5692
Max Act: 8.0692. Min Act: -0.1700
Data Index: 3937797 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5692. Min Range: -8.5692
Max Act: 8.0067. Min Act: -0.1700
Data Index: 1134951 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5692. Min Range: -8.5692
Max Act: 8.0067. Min Act: -0.1700
Data Index: 988600 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5692. Min Range: -8.5692
Max Act: 7.9442. Min Act: -0.1700
Data Index: 6763105 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5692. Min Range: -8.5692
Max Act: 7.8817. Min Act: -0.1700
Data Index: 8422625 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5692. Min Range: -8.5692
Max Act: 7.8817. Min Act: -0.1700
Data Index: 799551 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5692. Min Range: -8.5692
Max Act: 7.8192. Min Act: -0.1700
Data Index: 2450243 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5692. Min Range: -8.5692
Max Act: 7.8192. Min Act: -0.1700
Data Index: 4672146 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5692. Min Range: -8.5692
Max Act: 7.7567. Min Act: -0.1700
Data Index: 975520 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5692. Min Range: -8.5692
Max Act: 7.7567. Min Act: -0.1700
Data Index: 2310834 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5692. Min Range: -8.5692
Max Act: 7.7567. Min Act: -0.1700
Data Index: 769356 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5692. Min Range: -8.5692
Max Act: 7.6942. Min Act: -0.1700
Data Index: 7457025 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5692. Min Range: -8.5692
Max Act: 7.6942. Min Act: -0.1700
Data Index: 4358882 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5692. Min Range: -8.5692
Max Act: 7.6317. Min Act: -0.1700
Data Index: 7991526 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5692. Min Range: -8.5692
Max Act: 7.6317. Min Act: -0.1700
Data Index: 2508318 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5692. Min Range: -8.5692
Max Act: 7.6317. Min Act: -0.1700
Data Index: 8564430 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5692. Min Range: -8.5692
Max Act: 7.6942. Min Act: -0.1700
Data Index: 1728125 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5692. Min Range: -8.5692
Max Act: 7.5692. Min Act: -0.1700
Data Index: 4238011 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19