Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1654 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7242. Min Range: -6.7242
Max Act: 6.7242. Min Act: -0.1700
Data Index: 3938289 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7242. Min Range: -6.7242
Max Act: 6.5992. Min Act: -0.1700
Data Index: 6886811 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7242. Min Range: -6.7242
Max Act: 6.3180. Min Act: -0.1700
Data Index: 3296190 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7242. Min Range: -6.7242
Max Act: 6.3180. Min Act: -0.1700
Data Index: 857759 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7242. Min Range: -6.7242
Max Act: 6.3180. Min Act: -0.1700
Data Index: 1575236 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7242. Min Range: -6.7242
Max Act: 6.2867. Min Act: -0.1700
Data Index: 4925723 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7242. Min Range: -6.7242
Max Act: 6.2867. Min Act: -0.1700
Data Index: 4596036 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7242. Min Range: -6.7242
Max Act: 6.2555. Min Act: -0.1700
Data Index: 7972174 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7242. Min Range: -6.7242
Max Act: 6.2242. Min Act: -0.1700
Data Index: 1133630 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7242. Min Range: -6.7242
Max Act: 6.2242. Min Act: -0.1700
Data Index: 817627 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7242. Min Range: -6.7242
Max Act: 6.2242. Min Act: -0.1700
Data Index: 4009074 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7242. Min Range: -6.7242
Max Act: 6.1930. Min Act: -0.1700
Data Index: 3007466 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7242. Min Range: -6.7242
Max Act: 6.1617. Min Act: -0.1700
Data Index: 4157994 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7242. Min Range: -6.7242
Max Act: 6.1930. Min Act: -0.1700
Data Index: 5843058 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7242. Min Range: -6.7242
Max Act: 6.1305. Min Act: -0.1700
Data Index: 4336413 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7242. Min Range: -6.7242
Max Act: 6.1305. Min Act: -0.1700
Data Index: 3061297 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7242. Min Range: -6.7242
Max Act: 6.1305. Min Act: -0.1700
Data Index: 950982 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7242. Min Range: -6.7242
Max Act: 6.1305. Min Act: -0.1700
Data Index: 3778621 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7242. Min Range: -6.7242
Max Act: 6.0992. Min Act: -0.1700
Data Index: 3925437 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7242. Min Range: -6.7242
Max Act: 6.0992. Min Act: -0.1700
Data Index: 3770902 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #19