Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5645 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7546. Min Range: -8.7546
Max Act: 8.7546. Min Act: -0.1700
Data Index: 4832623 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7546. Min Range: -8.7546
Max Act: 8.5671. Min Act: -0.1700
Data Index: 2709595 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7546. Min Range: -8.7546
Max Act: 8.2858. Min Act: -0.1700
Data Index: 4954912 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7546. Min Range: -8.7546
Max Act: 8.2858. Min Act: -0.1700
Data Index: 2309244 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7546. Min Range: -8.7546
Max Act: 8.2233. Min Act: -0.1700
Data Index: 5504921 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7546. Min Range: -8.7546
Max Act: 8.2546. Min Act: -0.1700
Data Index: 2879156 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7546. Min Range: -8.7546
Max Act: 8.0046. Min Act: -0.1700
Data Index: 7753030 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7546. Min Range: -8.7546
Max Act: 8.0046. Min Act: -0.1700
Data Index: 4096157 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7546. Min Range: -8.7546
Max Act: 8.0046. Min Act: -0.1700
Data Index: 8692284 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7546. Min Range: -8.7546
Max Act: 7.9733. Min Act: -0.1700
Data Index: 518774 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7546. Min Range: -8.7546
Max Act: 7.9421. Min Act: -0.1700
Data Index: 262006 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7546. Min Range: -8.7546
Max Act: 7.8796. Min Act: -0.1700
Data Index: 1626636 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7546. Min Range: -8.7546
Max Act: 7.8483. Min Act: -0.1700
Data Index: 625646 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7546. Min Range: -8.7546
Max Act: 7.8796. Min Act: -0.1700
Data Index: 2878132 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7546. Min Range: -8.7546
Max Act: 7.8483. Min Act: -0.1700
Data Index: 5154099 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7546. Min Range: -8.7546
Max Act: 7.7858. Min Act: -0.1700
Data Index: 2044515 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7546. Min Range: -8.7546
Max Act: 7.8483. Min Act: -0.1700
Data Index: 1763034 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7546. Min Range: -8.7546
Max Act: 7.8171. Min Act: -0.1700
Data Index: 5245324 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7546. Min Range: -8.7546
Max Act: 7.7858. Min Act: -0.1699
Data Index: 1008319 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7546. Min Range: -8.7546
Max Act: 7.7546. Min Act: -0.1700
Data Index: 1966475 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #19