Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4642 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5542. Min Range: -2.5542
Max Act: 2.5542. Min Act: -0.1700
Data Index: 2643141 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5542. Min Range: -2.5542
Max Act: 2.5542. Min Act: -0.1699
Data Index: 5775445 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5542. Min Range: -2.5542
Max Act: 2.5380. Min Act: -0.1700
Data Index: 7966817 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5542. Min Range: -2.5542
Max Act: 2.5380. Min Act: -0.1700
Data Index: 7961108 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5542. Min Range: -2.5542
Max Act: 2.5218. Min Act: -0.1700
Data Index: 6140822 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5542. Min Range: -2.5542
Max Act: 2.5218. Min Act: -0.1700
Data Index: 6592054 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5542. Min Range: -2.5542
Max Act: 2.5057. Min Act: -0.1700
Data Index: 1533097 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5542. Min Range: -2.5542
Max Act: 2.5057. Min Act: -0.1700
Data Index: 4759412 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5542. Min Range: -2.5542
Max Act: 2.5057. Min Act: -0.1700
Data Index: 3360820 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5542. Min Range: -2.5542
Max Act: 2.4895. Min Act: -0.1700
Data Index: 5281549 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5542. Min Range: -2.5542
Max Act: 2.4732. Min Act: -0.1700
Data Index: 6281201 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5542. Min Range: -2.5542
Max Act: 2.4570. Min Act: -0.1700
Data Index: 1811142 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5542. Min Range: -2.5542
Max Act: 2.4732. Min Act: -0.1700
Data Index: 5064736 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5542. Min Range: -2.5542
Max Act: 2.4732. Min Act: -0.1700
Data Index: 5303736 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5542. Min Range: -2.5542
Max Act: 2.4895. Min Act: -0.1700
Data Index: 2538314 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5542. Min Range: -2.5542
Max Act: 2.4895. Min Act: -0.1700
Data Index: 7203575 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5542. Min Range: -2.5542
Max Act: 2.4732. Min Act: -0.1700
Data Index: 7004293 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5542. Min Range: -2.5542
Max Act: 2.4895. Min Act: -0.1700
Data Index: 3490344 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5542. Min Range: -2.5542
Max Act: 2.4732. Min Act: -0.1700
Data Index: 2643146 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5542. Min Range: -2.5542
Max Act: 2.4732. Min Act: -0.1700
Data Index: 6624226 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19