Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4726 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2207. Min Range: -7.2207
Max Act: 7.2207. Min Act: -0.1700
Data Index: 8255314 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2207. Min Range: -7.2207
Max Act: 7.1895. Min Act: -0.1700
Data Index: 6163618 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2207. Min Range: -7.2207
Max Act: 7.0332. Min Act: -0.1700
Data Index: 2115857 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.9395. Min Act: -0.1700
Data Index: 8790877 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.7520. Min Act: -0.1700
Data Index: 1144693 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.7207. Min Act: -0.1700
Data Index: 960593 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.6582. Min Act: -0.1700
Data Index: 6515063 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.6895. Min Act: -0.1700
Data Index: 4749183 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.7207. Min Act: -0.1700
Data Index: 3598190 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.6895. Min Act: -0.1700
Data Index: 1829796 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.5645. Min Act: -0.1700
Data Index: 6284159 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.5332. Min Act: -0.1700
Data Index: 6163615 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.5332. Min Act: -0.1700
Data Index: 4669046 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.5020. Min Act: -0.1700
Data Index: 3445963 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.4707. Min Act: -0.1700
Data Index: 2315871 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.5020. Min Act: -0.1700
Data Index: 3557151 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.4707. Min Act: -0.1700
Data Index: 5659702 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.5020. Min Act: -0.1700
Data Index: 6760044 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.4707. Min Act: -0.1700
Data Index: 8316457 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2207. Min Range: -7.2207
Max Act: 6.5020. Min Act: -0.1700
Data Index: 4660587 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19