Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3773 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6878. Min Range: -7.6878
Max Act: 7.6878. Min Act: -0.1700
Data Index: 2555803 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6878. Min Range: -7.6878
Max Act: 7.0315. Min Act: -0.1700
Data Index: 2845214 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6878. Min Range: -7.6878
Max Act: 6.8753. Min Act: -0.1700
Data Index: 322914 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6878. Min Range: -7.6878
Max Act: 6.8753. Min Act: -0.1700
Data Index: 2479691 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6878. Min Range: -7.6878
Max Act: 6.7190. Min Act: -0.1700
Data Index: 6154025 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6878. Min Range: -7.6878
Max Act: 6.6565. Min Act: -0.1700
Data Index: 2478869 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6878. Min Range: -7.6878
Max Act: 6.6253. Min Act: -0.1700
Data Index: 2807142 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6878. Min Range: -7.6878
Max Act: 6.4690. Min Act: -0.1700
Data Index: 3811625 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6878. Min Range: -7.6878
Max Act: 6.4065. Min Act: -0.1700
Data Index: 5925297 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6878. Min Range: -7.6878
Max Act: 6.4378. Min Act: -0.1700
Data Index: 6541125 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6878. Min Range: -7.6878
Max Act: 6.3753. Min Act: -0.1700
Data Index: 8670702 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6878. Min Range: -7.6878
Max Act: 6.3753. Min Act: -0.1700
Data Index: 1304308 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6878. Min Range: -7.6878
Max Act: 6.3440. Min Act: -0.1700
Data Index: 3279085 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6878. Min Range: -7.6878
Max Act: 6.3440. Min Act: -0.1700
Data Index: 3818751 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6878. Min Range: -7.6878
Max Act: 6.3128. Min Act: -0.1700
Data Index: 5432985 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6878. Min Range: -7.6878
Max Act: 6.3440. Min Act: -0.1700
Data Index: 1865758 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6878. Min Range: -7.6878
Max Act: 6.3128. Min Act: -0.1700
Data Index: 7043595 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6878. Min Range: -7.6878
Max Act: 6.3128. Min Act: -0.1700
Data Index: 8358389 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6878. Min Range: -7.6878
Max Act: 6.3128. Min Act: -0.1700
Data Index: 43715 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6878. Min Range: -7.6878
Max Act: 6.3128. Min Act: -0.1700
Data Index: 3734051 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19