Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3336 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2156. Min Range: -5.2156
Max Act: 5.2156. Min Act: -0.1700
Data Index: 7044852 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2156. Min Range: -5.2156
Max Act: 5.0594. Min Act: -0.1700
Data Index: 7817441 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.9969. Min Act: -0.1700
Data Index: 5332434 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.9656. Min Act: -0.1700
Data Index: 5830134 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.9656. Min Act: -0.1700
Data Index: 1084138 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.9344. Min Act: -0.1700
Data Index: 5830135 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.9031. Min Act: -0.1700
Data Index: 3903703 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.9031. Min Act: -0.1700
Data Index: 8499085 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.9031. Min Act: -0.1700
Data Index: 627694 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.9031. Min Act: -0.1700
Data Index: 7406916 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.8719. Min Act: -0.1700
Data Index: 7464727 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.8719. Min Act: -0.1700
Data Index: 6327573 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.8406. Min Act: -0.1700
Data Index: 5730751 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.8719. Min Act: -0.1700
Data Index: 2905841 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.8406. Min Act: -0.1700
Data Index: 4294435 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.8406. Min Act: -0.1700
Data Index: 4364358 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.8406. Min Act: -0.1700
Data Index: 4045625 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.8406. Min Act: -0.1700
Data Index: 6588752 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.8094. Min Act: -0.1700
Data Index: 33838 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2156. Min Range: -5.2156
Max Act: 4.7781. Min Act: -0.1700
Data Index: 2122555 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19