Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3943 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3929. Min Range: -7.3929
Max Act: 7.3929. Min Act: -0.1700
Data Index: 5242467 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3929. Min Range: -7.3929
Max Act: 7.2991. Min Act: -0.1700
Data Index: 1376312 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3929. Min Range: -7.3929
Max Act: 7.2366. Min Act: -0.1700
Data Index: 3545834 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3929. Min Range: -7.3929
Max Act: 7.2054. Min Act: -0.1700
Data Index: 3244830 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3929. Min Range: -7.3929
Max Act: 7.2054. Min Act: -0.1700
Data Index: 1701746 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3929. Min Range: -7.3929
Max Act: 7.1116. Min Act: -0.1700
Data Index: 368768 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3929. Min Range: -7.3929
Max Act: 7.1116. Min Act: -0.1700
Data Index: 5510665 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3929. Min Range: -7.3929
Max Act: 7.0491. Min Act: -0.1700
Data Index: 5242473 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3929. Min Range: -7.3929
Max Act: 6.9866. Min Act: -0.1700
Data Index: 7828003 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3929. Min Range: -7.3929
Max Act: 6.9241. Min Act: -0.1700
Data Index: 6492348 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3929. Min Range: -7.3929
Max Act: 6.9241. Min Act: -0.1700
Data Index: 8442689 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3929. Min Range: -7.3929
Max Act: 6.9241. Min Act: -0.1700
Data Index: 3566317 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3929. Min Range: -7.3929
Max Act: 6.8929. Min Act: -0.1700
Data Index: 7327984 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3929. Min Range: -7.3929
Max Act: 6.9241. Min Act: -0.1700
Data Index: 7516446 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3929. Min Range: -7.3929
Max Act: 6.9241. Min Act: -0.1700
Data Index: 8221661 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3929. Min Range: -7.3929
Max Act: 6.8929. Min Act: -0.1700
Data Index: 6507557 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3929. Min Range: -7.3929
Max Act: 6.8616. Min Act: -0.1700
Data Index: 5656863 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3929. Min Range: -7.3929
Max Act: 6.8304. Min Act: -0.1700
Data Index: 2900300 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3929. Min Range: -7.3929
Max Act: 6.8304. Min Act: -0.1700
Data Index: 3342044 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3929. Min Range: -7.3929
Max Act: 6.8304. Min Act: -0.1700
Data Index: 1996926 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19