Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 611 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7782. Min Range: -5.7782
Max Act: 5.7782. Min Act: -0.1700
Data Index: 3186694 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7782. Min Range: -5.7782
Max Act: 5.4657. Min Act: -0.1700
Data Index: 2157903 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7782. Min Range: -5.7782
Max Act: 5.4657. Min Act: -0.1700
Data Index: 130507 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7782. Min Range: -5.7782
Max Act: 5.4344. Min Act: -0.1700
Data Index: 951228 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7782. Min Range: -5.7782
Max Act: 5.4032. Min Act: -0.1700
Data Index: 1005217 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7782. Min Range: -5.7782
Max Act: 5.4032. Min Act: -0.1700
Data Index: 3582814 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7782. Min Range: -5.7782
Max Act: 5.3407. Min Act: -0.1700
Data Index: 6909909 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7782. Min Range: -5.7782
Max Act: 5.3407. Min Act: -0.1700
Data Index: 3963907 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7782. Min Range: -5.7782
Max Act: 5.3407. Min Act: -0.1700
Data Index: 4009515 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7782. Min Range: -5.7782
Max Act: 5.3094. Min Act: -0.1700
Data Index: 1867413 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7782. Min Range: -5.7782
Max Act: 5.3094. Min Act: -0.1700
Data Index: 1437926 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7782. Min Range: -5.7782
Max Act: 5.3094. Min Act: -0.1700
Data Index: 465814 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7782. Min Range: -5.7782
Max Act: 5.2782. Min Act: -0.1700
Data Index: 8660161 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7782. Min Range: -5.7782
Max Act: 5.2782. Min Act: -0.1700
Data Index: 1434623 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7782. Min Range: -5.7782
Max Act: 5.2782. Min Act: -0.1700
Data Index: 5022907 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7782. Min Range: -5.7782
Max Act: 5.2469. Min Act: -0.1700
Data Index: 3490936 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7782. Min Range: -5.7782
Max Act: 5.2469. Min Act: -0.1700
Data Index: 73770 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7782. Min Range: -5.7782
Max Act: 5.2157. Min Act: -0.1700
Data Index: 5969563 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7782. Min Range: -5.7782
Max Act: 5.2157. Min Act: -0.1700
Data Index: 1635490 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7782. Min Range: -5.7782
Max Act: 5.2469. Min Act: -0.1700
Data Index: 2975181 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19