Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1343 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4722. Min Range: -9.4722
Max Act: 9.4722. Min Act: -0.1700
Data Index: 2023245 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4722. Min Range: -9.4722
Max Act: 9.1597. Min Act: -0.1700
Data Index: 7913411 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4722. Min Range: -9.4722
Max Act: 9.0347. Min Act: -0.1700
Data Index: 3009650 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4722. Min Range: -9.4722
Max Act: 8.9722. Min Act: -0.1700
Data Index: 2271775 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4722. Min Range: -9.4722
Max Act: 8.9097. Min Act: -0.1700
Data Index: 788037 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4722. Min Range: -9.4722
Max Act: 8.9097. Min Act: -0.1700
Data Index: 4199856 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4722. Min Range: -9.4722
Max Act: 8.9097. Min Act: -0.1700
Data Index: 5173077 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4722. Min Range: -9.4722
Max Act: 8.8472. Min Act: -0.1700
Data Index: 8057738 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4722. Min Range: -9.4722
Max Act: 8.7847. Min Act: -0.1700
Data Index: 4726859 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4722. Min Range: -9.4722
Max Act: 8.7222. Min Act: -0.1700
Data Index: 3520410 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4722. Min Range: -9.4722
Max Act: 8.6597. Min Act: -0.1700
Data Index: 8344136 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4722. Min Range: -9.4722
Max Act: 8.5972. Min Act: -0.1700
Data Index: 944750 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4722. Min Range: -9.4722
Max Act: 8.5972. Min Act: -0.1700
Data Index: 6707848 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4722. Min Range: -9.4722
Max Act: 8.5972. Min Act: -0.1700
Data Index: 8092852 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4722. Min Range: -9.4722
Max Act: 8.5972. Min Act: -0.1700
Data Index: 1841988 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4722. Min Range: -9.4722
Max Act: 8.5972. Min Act: -0.1700
Data Index: 7555861 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4722. Min Range: -9.4722
Max Act: 8.5972. Min Act: -0.1700
Data Index: 3788428 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4722. Min Range: -9.4722
Max Act: 8.5972. Min Act: -0.1700
Data Index: 7728170 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4722. Min Range: -9.4722
Max Act: 8.5347. Min Act: -0.1700
Data Index: 2633700 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4722. Min Range: -9.4722
Max Act: 8.5347. Min Act: -0.1700
Data Index: 7492917 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19