Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2941 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5681. Min Range: -6.5681
Max Act: 6.5681. Min Act: -0.1700
Data Index: 7469724 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5681. Min Range: -6.5681
Max Act: 6.4119. Min Act: -0.1700
Data Index: 7745375 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5681. Min Range: -6.5681
Max Act: 6.4119. Min Act: -0.1700
Data Index: 4435761 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5681. Min Range: -6.5681
Max Act: 6.3806. Min Act: -0.1700
Data Index: 720530 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5681. Min Range: -6.5681
Max Act: 6.3494. Min Act: -0.1700
Data Index: 6578214 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5681. Min Range: -6.5681
Max Act: 6.3494. Min Act: -0.1700
Data Index: 5354429 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5681. Min Range: -6.5681
Max Act: 6.3494. Min Act: -0.1700
Data Index: 7337192 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5681. Min Range: -6.5681
Max Act: 6.3181. Min Act: -0.1700
Data Index: 426898 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5681. Min Range: -6.5681
Max Act: 6.3181. Min Act: -0.1700
Data Index: 7277600 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5681. Min Range: -6.5681
Max Act: 6.3181. Min Act: -0.1700
Data Index: 4753199 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5681. Min Range: -6.5681
Max Act: 6.2556. Min Act: -0.1700
Data Index: 83646 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5681. Min Range: -6.5681
Max Act: 6.2556. Min Act: -0.1700
Data Index: 3788427 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5681. Min Range: -6.5681
Max Act: 6.2244. Min Act: -0.1700
Data Index: 1415428 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5681. Min Range: -6.5681
Max Act: 6.2244. Min Act: -0.1700
Data Index: 141372 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5681. Min Range: -6.5681
Max Act: 6.2244. Min Act: -0.1700
Data Index: 2827835 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5681. Min Range: -6.5681
Max Act: 6.2556. Min Act: -0.1700
Data Index: 6265094 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5681. Min Range: -6.5681
Max Act: 6.1931. Min Act: -0.1700
Data Index: 349220 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5681. Min Range: -6.5681
Max Act: 6.1931. Min Act: -0.1700
Data Index: 1822345 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5681. Min Range: -6.5681
Max Act: 6.1931. Min Act: -0.1700
Data Index: 4381790 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5681. Min Range: -6.5681
Max Act: 6.1619. Min Act: -0.1700
Data Index: 1628758 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #19