Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4902 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.5762. Min Range: -11.5762
Max Act: 11.5762. Min Act: -0.1700
Data Index: 3884836 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.5762. Min Range: -11.5762
Max Act: 11.5137. Min Act: -0.1700
Data Index: 3884843 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.5762. Min Range: -11.5762
Max Act: 11.4512. Min Act: -0.1700
Data Index: 2033698 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.5762. Min Range: -11.5762
Max Act: 11.1387. Min Act: -0.1700
Data Index: 6707679 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.5762. Min Range: -11.5762
Max Act: 11.0762. Min Act: -0.1700
Data Index: 6158705 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.5762. Min Range: -11.5762
Max Act: 11.1387. Min Act: -0.1700
Data Index: 3884831 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.5762. Min Range: -11.5762
Max Act: 10.9512. Min Act: -0.1700
Data Index: 3848833 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.5762. Min Range: -11.5762
Max Act: 10.7637. Min Act: -0.1700
Data Index: 3884811 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.5762. Min Range: -11.5762
Max Act: 10.7637. Min Act: -0.1700
Data Index: 3649063 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.5762. Min Range: -11.5762
Max Act: 10.7637. Min Act: -0.1700
Data Index: 3249488 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.5762. Min Range: -11.5762
Max Act: 10.6387. Min Act: -0.1700
Data Index: 7387222 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.5762. Min Range: -11.5762
Max Act: 10.6387. Min Act: -0.1700
Data Index: 7624598 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.5762. Min Range: -11.5762
Max Act: 10.6387. Min Act: -0.1700
Data Index: 3884825 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.5762. Min Range: -11.5762
Max Act: 10.6387. Min Act: -0.1700
Data Index: 3884807 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.5762. Min Range: -11.5762
Max Act: 10.5137. Min Act: -0.1700
Data Index: 2033704 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.5762. Min Range: -11.5762
Max Act: 10.5137. Min Act: -0.1700
Data Index: 5128011 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.5762. Min Range: -11.5762
Max Act: 10.4512. Min Act: -0.1700
Data Index: 6707680 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.5762. Min Range: -11.5762
Max Act: 10.4512. Min Act: -0.1700
Data Index: 7387237 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.5762. Min Range: -11.5762
Max Act: 10.4512. Min Act: -0.1700
Data Index: 3884822 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.5762. Min Range: -11.5762
Max Act: 10.3887. Min Act: -0.1700
Data Index: 1046452 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19