Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3509 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9007. Min Range: -6.9007
Max Act: 6.9007. Min Act: -0.1700
Data Index: 2073790 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9007. Min Range: -6.9007
Max Act: 6.8070. Min Act: -0.1700
Data Index: 2776898 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9007. Min Range: -6.9007
Max Act: 6.6507. Min Act: -0.1700
Data Index: 1072333 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9007. Min Range: -6.9007
Max Act: 6.6195. Min Act: -0.1700
Data Index: 1483811 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9007. Min Range: -6.9007
Max Act: 6.6195. Min Act: -0.1700
Data Index: 5519625 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9007. Min Range: -6.9007
Max Act: 6.5257. Min Act: -0.1700
Data Index: 3117119 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9007. Min Range: -6.9007
Max Act: 6.5570. Min Act: -0.1700
Data Index: 5369614 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9007. Min Range: -6.9007
Max Act: 6.4320. Min Act: -0.1700
Data Index: 1851512 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9007. Min Range: -6.9007
Max Act: 6.3695. Min Act: -0.1700
Data Index: 708384 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9007. Min Range: -6.9007
Max Act: 6.3695. Min Act: -0.1700
Data Index: 5543786 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9007. Min Range: -6.9007
Max Act: 6.3382. Min Act: -0.1700
Data Index: 8790727 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9007. Min Range: -6.9007
Max Act: 6.3695. Min Act: -0.1700
Data Index: 8808454 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9007. Min Range: -6.9007
Max Act: 6.3695. Min Act: -0.1700
Data Index: 105564 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9007. Min Range: -6.9007
Max Act: 6.3382. Min Act: -0.1700
Data Index: 6990910 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9007. Min Range: -6.9007
Max Act: 6.3070. Min Act: -0.1700
Data Index: 954388 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9007. Min Range: -6.9007
Max Act: 6.3070. Min Act: -0.1700
Data Index: 848142 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9007. Min Range: -6.9007
Max Act: 6.2757. Min Act: -0.1700
Data Index: 1348864 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9007. Min Range: -6.9007
Max Act: 6.3070. Min Act: -0.1700
Data Index: 955243 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9007. Min Range: -6.9007
Max Act: 6.2757. Min Act: -0.1700
Data Index: 2307410 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9007. Min Range: -6.9007
Max Act: 6.2757. Min Act: -0.1700
Data Index: 8150367 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #19