Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 838 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5682. Min Range: -6.5682
Max Act: 6.5682. Min Act: -0.1700
Data Index: 586124 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5682. Min Range: -6.5682
Max Act: 6.5370. Min Act: -0.1700
Data Index: 7827170 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5682. Min Range: -6.5682
Max Act: 6.5057. Min Act: -0.1700
Data Index: 1051035 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5682. Min Range: -6.5682
Max Act: 6.5057. Min Act: -0.1700
Data Index: 6923296 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5682. Min Range: -6.5682
Max Act: 6.4745. Min Act: -0.1700
Data Index: 284043 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5682. Min Range: -6.5682
Max Act: 6.5057. Min Act: -0.1700
Data Index: 8143161 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5682. Min Range: -6.5682
Max Act: 6.4432. Min Act: -0.1700
Data Index: 161060 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5682. Min Range: -6.5682
Max Act: 6.4432. Min Act: -0.1700
Data Index: 6076555 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5682. Min Range: -6.5682
Max Act: 6.4120. Min Act: -0.1700
Data Index: 8228447 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5682. Min Range: -6.5682
Max Act: 6.4120. Min Act: -0.1700
Data Index: 6526091 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5682. Min Range: -6.5682
Max Act: 6.4120. Min Act: -0.1700
Data Index: 7402569 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5682. Min Range: -6.5682
Max Act: 6.4432. Min Act: -0.1700
Data Index: 6234602 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5682. Min Range: -6.5682
Max Act: 6.4120. Min Act: -0.1700
Data Index: 643311 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5682. Min Range: -6.5682
Max Act: 6.3807. Min Act: -0.1700
Data Index: 6659448 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5682. Min Range: -6.5682
Max Act: 6.3807. Min Act: -0.1700
Data Index: 892993 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5682. Min Range: -6.5682
Max Act: 6.3807. Min Act: -0.1700
Data Index: 4530694 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5682. Min Range: -6.5682
Max Act: 6.4120. Min Act: -0.1700
Data Index: 4607006 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5682. Min Range: -6.5682
Max Act: 6.3495. Min Act: -0.1700
Data Index: 1983860 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5682. Min Range: -6.5682
Max Act: 6.3495. Min Act: -0.1700
Data Index: 8688007 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5682. Min Range: -6.5682
Max Act: 6.3495. Min Act: -0.1700
Data Index: 2195649 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #19