Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5727 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9031. Min Range: -6.9031
Max Act: 6.9031. Min Act: -0.1700
Data Index: 808723 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9031. Min Range: -6.9031
Max Act: 6.7781. Min Act: -0.1700
Data Index: 6989356 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9031. Min Range: -6.9031
Max Act: 6.6843. Min Act: -0.1700
Data Index: 6989353 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9031. Min Range: -6.9031
Max Act: 6.7156. Min Act: -0.1700
Data Index: 6989352 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9031. Min Range: -6.9031
Max Act: 6.5281. Min Act: -0.1700
Data Index: 1779995 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9031. Min Range: -6.9031
Max Act: 6.4968. Min Act: -0.1700
Data Index: 6989355 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9031. Min Range: -6.9031
Max Act: 6.4656. Min Act: -0.1700
Data Index: 1779997 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9031. Min Range: -6.9031
Max Act: 6.4343. Min Act: -0.1700
Data Index: 7540128 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9031. Min Range: -6.9031
Max Act: 6.3406. Min Act: -0.1700
Data Index: 5564195 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9031. Min Range: -6.9031
Max Act: 6.3406. Min Act: -0.1700
Data Index: 3199060 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9031. Min Range: -6.9031
Max Act: 6.2781. Min Act: -0.1700
Data Index: 4912364 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9031. Min Range: -6.9031
Max Act: 6.2781. Min Act: -0.1700
Data Index: 1086926 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9031. Min Range: -6.9031
Max Act: 6.2468. Min Act: -0.1700
Data Index: 1779990 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9031. Min Range: -6.9031
Max Act: 6.2468. Min Act: -0.1700
Data Index: 4450726 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9031. Min Range: -6.9031
Max Act: 6.2468. Min Act: -0.1700
Data Index: 1037748 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9031. Min Range: -6.9031
Max Act: 6.2468. Min Act: -0.1700
Data Index: 1596257 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9031. Min Range: -6.9031
Max Act: 6.2156. Min Act: -0.1700
Data Index: 2009473 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9031. Min Range: -6.9031
Max Act: 6.2468. Min Act: -0.1700
Data Index: 3938833 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9031. Min Range: -6.9031
Max Act: 6.2156. Min Act: -0.1700
Data Index: 2921784 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9031. Min Range: -6.9031
Max Act: 6.1843. Min Act: -0.1700
Data Index: 3079126 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19