Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4792 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4719. Min Range: -4.4719
Max Act: 4.4407. Min Act: -0.1700
Data Index: 7603217 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4719. Min Range: -4.4719
Max Act: 4.4407. Min Act: -0.1700
Data Index: 3997050 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4719. Min Range: -4.4719
Max Act: 4.4719. Min Act: -0.1700
Data Index: 8212221 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4719. Min Range: -4.4719
Max Act: 4.3469. Min Act: -0.1700
Data Index: 773573 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4719. Min Range: -4.4719
Max Act: 4.2219. Min Act: -0.1700
Data Index: 7086209 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4719. Min Range: -4.4719
Max Act: 4.2219. Min Act: -0.1700
Data Index: 8418921 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4719. Min Range: -4.4719
Max Act: 4.2219. Min Act: -0.1700
Data Index: 5574932 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4719. Min Range: -4.4719
Max Act: 4.1281. Min Act: -0.1700
Data Index: 7389495 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4719. Min Range: -4.4719
Max Act: 4.0969. Min Act: -0.1700
Data Index: 7175524 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4719. Min Range: -4.4719
Max Act: 4.1281. Min Act: -0.1700
Data Index: 5697974 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4719. Min Range: -4.4719
Max Act: 4.0969. Min Act: -0.1700
Data Index: 1843253 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4719. Min Range: -4.4719
Max Act: 4.1281. Min Act: -0.1700
Data Index: 3063057 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4719. Min Range: -4.4719
Max Act: 4.1594. Min Act: -0.1700
Data Index: 2968561 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4719. Min Range: -4.4719
Max Act: 4.0656. Min Act: -0.1700
Data Index: 2748581 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4719. Min Range: -4.4719
Max Act: 4.0969. Min Act: -0.1700
Data Index: 4786255 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4719. Min Range: -4.4719
Max Act: 4.0969. Min Act: -0.1700
Data Index: 7364191 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4719. Min Range: -4.4719
Max Act: 4.0656. Min Act: -0.1700
Data Index: 4521541 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4719. Min Range: -4.4719
Max Act: 4.0656. Min Act: -0.1700
Data Index: 128072 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4719. Min Range: -4.4719
Max Act: 4.0344. Min Act: -0.1700
Data Index: 7868907 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4719. Min Range: -4.4719
Max Act: 4.0656. Min Act: -0.1700
Data Index: 5978365 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19