Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 225 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0586. Min Range: -8.0586
Max Act: 8.0586. Min Act: -0.1700
Data Index: 1089322 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0586. Min Range: -8.0586
Max Act: 7.8086. Min Act: -0.1700
Data Index: 6835325 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0586. Min Range: -8.0586
Max Act: 7.6836. Min Act: -0.1700
Data Index: 8402792 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0586. Min Range: -8.0586
Max Act: 7.6211. Min Act: -0.1700
Data Index: 3343218 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0586. Min Range: -8.0586
Max Act: 7.6211. Min Act: -0.1700
Data Index: 7619841 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0586. Min Range: -8.0586
Max Act: 7.5898. Min Act: -0.1700
Data Index: 4403478 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0586. Min Range: -8.0586
Max Act: 7.5898. Min Act: -0.1700
Data Index: 5738033 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0586. Min Range: -8.0586
Max Act: 7.5586. Min Act: -0.1700
Data Index: 7409407 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0586. Min Range: -8.0586
Max Act: 7.5586. Min Act: -0.1700
Data Index: 1819478 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0586. Min Range: -8.0586
Max Act: 7.4961. Min Act: -0.1700
Data Index: 5505402 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0586. Min Range: -8.0586
Max Act: 7.4336. Min Act: -0.1700
Data Index: 7911833 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0586. Min Range: -8.0586
Max Act: 7.4336. Min Act: -0.1700
Data Index: 3620460 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0586. Min Range: -8.0586
Max Act: 7.4336. Min Act: -0.1700
Data Index: 4914234 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0586. Min Range: -8.0586
Max Act: 7.4023. Min Act: -0.1700
Data Index: 4166904 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0586. Min Range: -8.0586
Max Act: 7.4023. Min Act: -0.1700
Data Index: 1384855 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0586. Min Range: -8.0586
Max Act: 7.4023. Min Act: -0.1700
Data Index: 8283894 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0586. Min Range: -8.0586
Max Act: 7.4023. Min Act: -0.1700
Data Index: 8255661 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0586. Min Range: -8.0586
Max Act: 7.4336. Min Act: -0.1700
Data Index: 1349108 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0586. Min Range: -8.0586
Max Act: 7.4023. Min Act: -0.1700
Data Index: 7464492 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0586. Min Range: -8.0586
Max Act: 7.4023. Min Act: -0.1700
Data Index: 1336021 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19