Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4669 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3673. Min Range: -5.3673
Max Act: 5.3673. Min Act: -0.1700
Data Index: 3403369 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3673. Min Range: -5.3673
Max Act: 4.8673. Min Act: -0.1700
Data Index: 7420856 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3673. Min Range: -5.3673
Max Act: 4.8360. Min Act: -0.1700
Data Index: 1834825 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3673. Min Range: -5.3673
Max Act: 4.8048. Min Act: -0.1700
Data Index: 6766781 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3673. Min Range: -5.3673
Max Act: 4.8048. Min Act: -0.1700
Data Index: 236761 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3673. Min Range: -5.3673
Max Act: 4.7423. Min Act: -0.1700
Data Index: 3991147 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3673. Min Range: -5.3673
Max Act: 4.6485. Min Act: -0.1700
Data Index: 1337788 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3673. Min Range: -5.3673
Max Act: 4.6485. Min Act: -0.1700
Data Index: 2871493 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3673. Min Range: -5.3673
Max Act: 4.6485. Min Act: -0.1700
Data Index: 3019281 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3673. Min Range: -5.3673
Max Act: 4.6173. Min Act: -0.1700
Data Index: 541726 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3673. Min Range: -5.3673
Max Act: 4.5548. Min Act: -0.1700
Data Index: 2157422 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3673. Min Range: -5.3673
Max Act: 4.5860. Min Act: -0.1700
Data Index: 7472733 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3673. Min Range: -5.3673
Max Act: 4.5235. Min Act: -0.1700
Data Index: 7635410 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3673. Min Range: -5.3673
Max Act: 4.5235. Min Act: -0.1700
Data Index: 758128 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3673. Min Range: -5.3673
Max Act: 4.5548. Min Act: -0.1700
Data Index: 5869321 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3673. Min Range: -5.3673
Max Act: 4.4610. Min Act: -0.1700
Data Index: 1392851 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3673. Min Range: -5.3673
Max Act: 4.4923. Min Act: -0.1700
Data Index: 5927458 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3673. Min Range: -5.3673
Max Act: 4.4923. Min Act: -0.1700
Data Index: 6801901 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3673. Min Range: -5.3673
Max Act: 4.4923. Min Act: -0.1700
Data Index: 4890841 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3673. Min Range: -5.3673
Max Act: 4.4610. Min Act: -0.1700
Data Index: 1989171 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19