Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4492 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7870. Min Range: -5.7870
Max Act: 5.7870. Min Act: -0.1700
Data Index: 7123643 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7870. Min Range: -5.7870
Max Act: 5.6307. Min Act: -0.1700
Data Index: 6452528 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7870. Min Range: -5.7870
Max Act: 5.6307. Min Act: -0.1700
Data Index: 2552699 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7870. Min Range: -5.7870
Max Act: 5.5995. Min Act: -0.1700
Data Index: 4093805 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7870. Min Range: -5.7870
Max Act: 5.5370. Min Act: -0.1700
Data Index: 623721 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7870. Min Range: -5.7870
Max Act: 5.5057. Min Act: -0.1700
Data Index: 8315219 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7870. Min Range: -5.7870
Max Act: 5.4745. Min Act: -0.1700
Data Index: 7602545 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7870. Min Range: -5.7870
Max Act: 5.4745. Min Act: -0.1700
Data Index: 4515724 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7870. Min Range: -5.7870
Max Act: 5.4745. Min Act: -0.1700
Data Index: 3083186 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7870. Min Range: -5.7870
Max Act: 5.4745. Min Act: -0.1700
Data Index: 8049655 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7870. Min Range: -5.7870
Max Act: 5.4432. Min Act: -0.1700
Data Index: 6616527 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7870. Min Range: -5.7870
Max Act: 5.4120. Min Act: -0.1700
Data Index: 6056078 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7870. Min Range: -5.7870
Max Act: 5.4120. Min Act: -0.1700
Data Index: 348718 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7870. Min Range: -5.7870
Max Act: 5.4120. Min Act: -0.1700
Data Index: 8094747 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7870. Min Range: -5.7870
Max Act: 5.3807. Min Act: -0.1700
Data Index: 6701411 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7870. Min Range: -5.7870
Max Act: 5.3807. Min Act: -0.1700
Data Index: 5241547 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7870. Min Range: -5.7870
Max Act: 5.3807. Min Act: -0.1700
Data Index: 4446239 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7870. Min Range: -5.7870
Max Act: 5.3807. Min Act: -0.1700
Data Index: 2763939 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7870. Min Range: -5.7870
Max Act: 5.3807. Min Act: -0.1700
Data Index: 3117827 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7870. Min Range: -5.7870
Max Act: 5.3495. Min Act: -0.1700
Data Index: 5651443 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19