Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2688 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0910. Min Range: -6.0910
Max Act: 6.0910. Min Act: -0.1700
Data Index: 897386 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0910. Min Range: -6.0910
Max Act: 6.0285. Min Act: -0.1700
Data Index: 4524787 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0910. Min Range: -6.0910
Max Act: 5.8410. Min Act: -0.1700
Data Index: 2208373 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0910. Min Range: -6.0910
Max Act: 5.7472. Min Act: -0.1700
Data Index: 61295 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0910. Min Range: -6.0910
Max Act: 5.7160. Min Act: -0.1700
Data Index: 5831279 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0910. Min Range: -6.0910
Max Act: 5.6847. Min Act: -0.1700
Data Index: 6193855 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0910. Min Range: -6.0910
Max Act: 5.6847. Min Act: -0.1700
Data Index: 7930626 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0910. Min Range: -6.0910
Max Act: 5.6847. Min Act: -0.1700
Data Index: 8015289 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0910. Min Range: -6.0910
Max Act: 5.6847. Min Act: -0.1700
Data Index: 5470493 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0910. Min Range: -6.0910
Max Act: 5.6847. Min Act: -0.1700
Data Index: 5525420 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0910. Min Range: -6.0910
Max Act: 5.6847. Min Act: -0.1700
Data Index: 8388170 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0910. Min Range: -6.0910
Max Act: 5.6535. Min Act: -0.1700
Data Index: 548234 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0910. Min Range: -6.0910
Max Act: 5.6222. Min Act: -0.1700
Data Index: 3973136 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0910. Min Range: -6.0910
Max Act: 5.6222. Min Act: -0.1700
Data Index: 4515653 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0910. Min Range: -6.0910
Max Act: 5.6222. Min Act: -0.1700
Data Index: 1754777 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0910. Min Range: -6.0910
Max Act: 5.6222. Min Act: -0.1700
Data Index: 7059858 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0910. Min Range: -6.0910
Max Act: 5.6222. Min Act: -0.1700
Data Index: 285510 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0910. Min Range: -6.0910
Max Act: 5.5597. Min Act: -0.1700
Data Index: 5805181 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0910. Min Range: -6.0910
Max Act: 5.5910. Min Act: -0.1700
Data Index: 224000 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0910. Min Range: -6.0910
Max Act: 5.6222. Min Act: -0.1700
Data Index: 1638005 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19