Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4542 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.6161. Min Act: -0.1700
Data Index: 7499145 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.5536. Min Act: -0.1700
Data Index: 8093809 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.5536. Min Act: -0.1700
Data Index: 676373 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.5536. Min Act: -0.1700
Data Index: 4589960 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.5536. Min Act: -0.1700
Data Index: 38018 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.5224. Min Act: -0.1700
Data Index: 3645982 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.5224. Min Act: -0.1700
Data Index: 1071311 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.5224. Min Act: -0.1700
Data Index: 1858383 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.4911. Min Act: -0.1700
Data Index: 3154650 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.4911. Min Act: -0.1700
Data Index: 3446677 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.4911. Min Act: -0.1700
Data Index: 422482 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.4911. Min Act: -0.1700
Data Index: 8594431 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.4598. Min Act: -0.1700
Data Index: 6746049 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.4598. Min Act: -0.1700
Data Index: 3584672 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.4598. Min Act: -0.1700
Data Index: 6501664 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.4598. Min Act: -0.1700
Data Index: 4727503 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.4598. Min Act: -0.1700
Data Index: 6047700 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.4598. Min Act: -0.1700
Data Index: 4477142 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.4598. Min Act: -0.1700
Data Index: 8208829 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6161. Min Range: -4.6161
Max Act: 4.4286. Min Act: -0.1700
Data Index: 6170892 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #19