Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1289 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0111. Min Range: -7.0111
Max Act: 7.0111. Min Act: -0.1700
Data Index: 3604112 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0111. Min Range: -7.0111
Max Act: 6.7298. Min Act: -0.1700
Data Index: 6405669 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0111. Min Range: -7.0111
Max Act: 6.7298. Min Act: -0.1700
Data Index: 6405670 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0111. Min Range: -7.0111
Max Act: 6.6673. Min Act: -0.1700
Data Index: 2044755 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0111. Min Range: -7.0111
Max Act: 6.6361. Min Act: -0.1700
Data Index: 4661311 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0111. Min Range: -7.0111
Max Act: 6.5736. Min Act: -0.1700
Data Index: 1892429 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0111. Min Range: -7.0111
Max Act: 6.4798. Min Act: -0.1700
Data Index: 6270931 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0111. Min Range: -7.0111
Max Act: 6.4798. Min Act: -0.1700
Data Index: 1998628 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0111. Min Range: -7.0111
Max Act: 6.4798. Min Act: -0.1700
Data Index: 4528285 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0111. Min Range: -7.0111
Max Act: 6.4486. Min Act: -0.1700
Data Index: 4244250 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0111. Min Range: -7.0111
Max Act: 6.4486. Min Act: -0.1700
Data Index: 7545596 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0111. Min Range: -7.0111
Max Act: 6.4173. Min Act: -0.1700
Data Index: 1360362 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0111. Min Range: -7.0111
Max Act: 6.3861. Min Act: -0.1700
Data Index: 2471932 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0111. Min Range: -7.0111
Max Act: 6.3861. Min Act: -0.1700
Data Index: 797980 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0111. Min Range: -7.0111
Max Act: 6.3861. Min Act: -0.1700
Data Index: 3899747 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0111. Min Range: -7.0111
Max Act: 6.3548. Min Act: -0.1700
Data Index: 8472216 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0111. Min Range: -7.0111
Max Act: 6.3548. Min Act: -0.1700
Data Index: 827826 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0111. Min Range: -7.0111
Max Act: 6.3236. Min Act: -0.1700
Data Index: 3109638 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0111. Min Range: -7.0111
Max Act: 6.2923. Min Act: -0.1700
Data Index: 7588492 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0111. Min Range: -7.0111
Max Act: 6.1986. Min Act: -0.1700
Data Index: 5791535 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19