Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3433 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5746. Min Range: -6.5746
Max Act: 6.5746. Min Act: -0.1700
Data Index: 6700893 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5746. Min Range: -6.5746
Max Act: 6.5121. Min Act: -0.1700
Data Index: 1686303 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5746. Min Range: -6.5746
Max Act: 6.2934. Min Act: -0.1700
Data Index: 6199372 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5746. Min Range: -6.5746
Max Act: 6.2621. Min Act: -0.1700
Data Index: 5957411 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5746. Min Range: -6.5746
Max Act: 6.1996. Min Act: -0.1700
Data Index: 8831738 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5746. Min Range: -6.5746
Max Act: 6.2309. Min Act: -0.1700
Data Index: 7838220 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5746. Min Range: -6.5746
Max Act: 6.2309. Min Act: -0.1700
Data Index: 1915971 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5746. Min Range: -6.5746
Max Act: 6.1684. Min Act: -0.1700
Data Index: 1069395 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5746. Min Range: -6.5746
Max Act: 6.1684. Min Act: -0.1700
Data Index: 2758407 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5746. Min Range: -6.5746
Max Act: 6.1059. Min Act: -0.1700
Data Index: 6693923 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5746. Min Range: -6.5746
Max Act: 6.1059. Min Act: -0.1700
Data Index: 129160 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5746. Min Range: -6.5746
Max Act: 6.1059. Min Act: -0.1700
Data Index: 8046131 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5746. Min Range: -6.5746
Max Act: 6.1059. Min Act: -0.1700
Data Index: 7795309 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5746. Min Range: -6.5746
Max Act: 6.1059. Min Act: -0.1700
Data Index: 642910 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5746. Min Range: -6.5746
Max Act: 6.0746. Min Act: -0.1700
Data Index: 7972867 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5746. Min Range: -6.5746
Max Act: 6.0746. Min Act: -0.1700
Data Index: 3174886 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5746. Min Range: -6.5746
Max Act: 6.0746. Min Act: -0.1700
Data Index: 1331907 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5746. Min Range: -6.5746
Max Act: 6.0434. Min Act: -0.1700
Data Index: 6212135 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5746. Min Range: -6.5746
Max Act: 6.0121. Min Act: -0.1700
Data Index: 1203170 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5746. Min Range: -6.5746
Max Act: 6.0121. Min Act: -0.1700
Data Index: 486590 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19