Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3440 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5729. Min Act: -0.1700
Data Index: 8350616 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5729. Min Act: -0.1700
Data Index: 7082988 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5416. Min Act: -0.1700
Data Index: 2954206 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5416. Min Act: -0.1700
Data Index: 2270611 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5416. Min Act: -0.1700
Data Index: 4482668 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5103. Min Act: -0.1700
Data Index: 2958884 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5103. Min Act: -0.1700
Data Index: 8626095 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5103. Min Act: -0.1700
Data Index: 7327295 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5103. Min Act: -0.1700
Data Index: 6918384 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5103. Min Act: -0.1700
Data Index: 4406233 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5103. Min Act: -0.1700
Data Index: 4237568 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5103. Min Act: -0.1700
Data Index: 4081968 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5103. Min Act: -0.1700
Data Index: 3853718 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.5103. Min Act: -0.1700
Data Index: 2954205 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.4790. Min Act: -0.1700
Data Index: 2707683 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.4790. Min Act: -0.1700
Data Index: 931967 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.4790. Min Act: -0.1700
Data Index: 2761011 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.4790. Min Act: -0.1700
Data Index: 961553 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.4790. Min Act: -0.1700
Data Index: 500215 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5729. Min Range: -3.5729
Max Act: 3.4790. Min Act: -0.1700
Data Index: 738638 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19