Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5100 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1102. Min Range: -7.1102
Max Act: 7.1102. Min Act: -0.1700
Data Index: 6268770 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1102. Min Range: -7.1102
Max Act: 7.0164. Min Act: -0.1700
Data Index: 6827542 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1102. Min Range: -7.1102
Max Act: 6.9852. Min Act: -0.1700
Data Index: 5187985 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1102. Min Range: -7.1102
Max Act: 6.9852. Min Act: -0.1700
Data Index: 2333520 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1102. Min Range: -7.1102
Max Act: 6.9227. Min Act: -0.1700
Data Index: 1692466 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1102. Min Range: -7.1102
Max Act: 6.9227. Min Act: -0.1700
Data Index: 5457262 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1102. Min Range: -7.1102
Max Act: 6.8289. Min Act: -0.1700
Data Index: 832080 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1102. Min Range: -7.1102
Max Act: 6.8914. Min Act: -0.1700
Data Index: 5493850 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1102. Min Range: -7.1102
Max Act: 6.8289. Min Act: -0.1700
Data Index: 1721680 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1102. Min Range: -7.1102
Max Act: 6.7352. Min Act: -0.1700
Data Index: 6364340 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1102. Min Range: -7.1102
Max Act: 6.7039. Min Act: -0.1700
Data Index: 4043372 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1102. Min Range: -7.1102
Max Act: 6.7039. Min Act: -0.1700
Data Index: 3767993 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1102. Min Range: -7.1102
Max Act: 6.6414. Min Act: -0.1700
Data Index: 2991463 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1102. Min Range: -7.1102
Max Act: 6.6414. Min Act: -0.1700
Data Index: 8333975 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1102. Min Range: -7.1102
Max Act: 6.4852. Min Act: -0.1700
Data Index: 7685910 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1102. Min Range: -7.1102
Max Act: 6.4539. Min Act: -0.1700
Data Index: 7090015 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1102. Min Range: -7.1102
Max Act: 6.4539. Min Act: -0.1700
Data Index: 4519736 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1102. Min Range: -7.1102
Max Act: 6.4227. Min Act: -0.1700
Data Index: 497175 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1102. Min Range: -7.1102
Max Act: 6.4227. Min Act: -0.1700
Data Index: 3864086 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1102. Min Range: -7.1102
Max Act: 6.3602. Min Act: -0.1700
Data Index: 1816846 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19