Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3404 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2906. Min Range: -5.2906
Max Act: 5.2906. Min Act: -0.1700
Data Index: 684156 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2906. Min Range: -5.2906
Max Act: 5.1031. Min Act: -0.1700
Data Index: 2366169 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2906. Min Range: -5.2906
Max Act: 5.0094. Min Act: -0.1700
Data Index: 2002900 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2906. Min Range: -5.2906
Max Act: 4.9156. Min Act: -0.1700
Data Index: 6856429 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2906. Min Range: -5.2906
Max Act: 4.8219. Min Act: -0.1700
Data Index: 3003901 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2906. Min Range: -5.2906
Max Act: 4.8531. Min Act: -0.1700
Data Index: 3744060 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2906. Min Range: -5.2906
Max Act: 4.8219. Min Act: -0.1700
Data Index: 8383874 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2906. Min Range: -5.2906
Max Act: 4.7906. Min Act: -0.1700
Data Index: 6318207 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2906. Min Range: -5.2906
Max Act: 4.7906. Min Act: -0.1700
Data Index: 7152142 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2906. Min Range: -5.2906
Max Act: 4.7906. Min Act: -0.1700
Data Index: 8786428 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2906. Min Range: -5.2906
Max Act: 4.7906. Min Act: -0.1700
Data Index: 7308149 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2906. Min Range: -5.2906
Max Act: 4.7594. Min Act: -0.1700
Data Index: 1480753 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2906. Min Range: -5.2906
Max Act: 4.7906. Min Act: -0.1700
Data Index: 2088677 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2906. Min Range: -5.2906
Max Act: 4.7281. Min Act: -0.1700
Data Index: 5603154 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2906. Min Range: -5.2906
Max Act: 4.7594. Min Act: -0.1700
Data Index: 3523251 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2906. Min Range: -5.2906
Max Act: 4.7281. Min Act: -0.1700
Data Index: 7791270 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2906. Min Range: -5.2906
Max Act: 4.6969. Min Act: -0.1700
Data Index: 7673139 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2906. Min Range: -5.2906
Max Act: 4.6969. Min Act: -0.1700
Data Index: 160384 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2906. Min Range: -5.2906
Max Act: 4.6969. Min Act: -0.1700
Data Index: 387062 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2906. Min Range: -5.2906
Max Act: 4.6656. Min Act: -0.1700
Data Index: 1500239 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19