Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5723 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1156. Min Range: -7.1156
Max Act: 7.1156. Min Act: -0.1700
Data Index: 6218211 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1156. Min Range: -7.1156
Max Act: 6.7406. Min Act: -0.1700
Data Index: 6441411 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1156. Min Range: -7.1156
Max Act: 6.7094. Min Act: -0.1700
Data Index: 3672129 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1156. Min Range: -7.1156
Max Act: 6.7094. Min Act: -0.1700
Data Index: 3452689 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1156. Min Range: -7.1156
Max Act: 6.6781. Min Act: -0.1700
Data Index: 4812998 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1156. Min Range: -7.1156
Max Act: 6.6156. Min Act: -0.1700
Data Index: 8736250 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1156. Min Range: -7.1156
Max Act: 6.5531. Min Act: -0.1700
Data Index: 6934129 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1156. Min Range: -7.1156
Max Act: 6.5219. Min Act: -0.1700
Data Index: 8438238 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1156. Min Range: -7.1156
Max Act: 6.4906. Min Act: -0.1700
Data Index: 4134117 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1156. Min Range: -7.1156
Max Act: 6.4906. Min Act: -0.1700
Data Index: 783926 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1156. Min Range: -7.1156
Max Act: 6.4594. Min Act: -0.1700
Data Index: 1582865 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1156. Min Range: -7.1156
Max Act: 6.3969. Min Act: -0.1700
Data Index: 4103734 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1156. Min Range: -7.1156
Max Act: 6.3656. Min Act: -0.1700
Data Index: 3804789 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1156. Min Range: -7.1156
Max Act: 6.3656. Min Act: -0.1700
Data Index: 4048543 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1156. Min Range: -7.1156
Max Act: 6.3656. Min Act: -0.1700
Data Index: 573328 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1156. Min Range: -7.1156
Max Act: 6.3656. Min Act: -0.1700
Data Index: 1040133 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1156. Min Range: -7.1156
Max Act: 6.3656. Min Act: -0.1700
Data Index: 4785917 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1156. Min Range: -7.1156
Max Act: 6.2719. Min Act: -0.1700
Data Index: 6082108 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1156. Min Range: -7.1156
Max Act: 6.2719. Min Act: -0.1700
Data Index: 6200121 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1156. Min Range: -7.1156
Max Act: 6.2094. Min Act: -0.1700
Data Index: 6604775 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19