Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3677 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3854. Min Range: -6.3854
Max Act: 6.3854. Min Act: -0.1700
Data Index: 1704639 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3854. Min Range: -6.3854
Max Act: 6.3542. Min Act: -0.1700
Data Index: 8740921 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3854. Min Range: -6.3854
Max Act: 6.2292. Min Act: -0.1700
Data Index: 687947 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3854. Min Range: -6.3854
Max Act: 6.1667. Min Act: -0.1700
Data Index: 116360 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3854. Min Range: -6.3854
Max Act: 6.1042. Min Act: -0.1700
Data Index: 5902457 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3854. Min Range: -6.3854
Max Act: 6.0729. Min Act: -0.1700
Data Index: 4923098 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3854. Min Range: -6.3854
Max Act: 5.9792. Min Act: -0.1700
Data Index: 4323442 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3854. Min Range: -6.3854
Max Act: 5.9792. Min Act: -0.1700
Data Index: 1690712 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3854. Min Range: -6.3854
Max Act: 5.9479. Min Act: -0.1700
Data Index: 6755018 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3854. Min Range: -6.3854
Max Act: 5.9479. Min Act: -0.1700
Data Index: 7883828 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3854. Min Range: -6.3854
Max Act: 5.9479. Min Act: -0.1700
Data Index: 6645208 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3854. Min Range: -6.3854
Max Act: 5.9479. Min Act: -0.1700
Data Index: 3134890 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3854. Min Range: -6.3854
Max Act: 5.9479. Min Act: -0.1700
Data Index: 4438865 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3854. Min Range: -6.3854
Max Act: 5.9167. Min Act: -0.1700
Data Index: 7121648 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3854. Min Range: -6.3854
Max Act: 5.9167. Min Act: -0.1700
Data Index: 4972491 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3854. Min Range: -6.3854
Max Act: 5.9167. Min Act: -0.1700
Data Index: 6931174 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3854. Min Range: -6.3854
Max Act: 5.8854. Min Act: -0.1700
Data Index: 8348476 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3854. Min Range: -6.3854
Max Act: 5.8854. Min Act: -0.1700
Data Index: 1175087 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3854. Min Range: -6.3854
Max Act: 5.8854. Min Act: -0.1700
Data Index: 5127277 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3854. Min Range: -6.3854
Max Act: 5.8854. Min Act: -0.1700
Data Index: 4488555 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19