Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2704 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4311. Min Range: -6.4311
Max Act: 6.3999. Min Act: -0.1700
Data Index: 1982489 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4311. Min Range: -6.4311
Max Act: 6.4311. Min Act: -0.1700
Data Index: 8670007 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4311. Min Range: -6.4311
Max Act: 6.3374. Min Act: -0.1700
Data Index: 198825 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4311. Min Range: -6.4311
Max Act: 6.2749. Min Act: -0.1700
Data Index: 6330074 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4311. Min Range: -6.4311
Max Act: 6.2436. Min Act: -0.1700
Data Index: 2692468 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4311. Min Range: -6.4311
Max Act: 6.1186. Min Act: -0.1700
Data Index: 1038571 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4311. Min Range: -6.4311
Max Act: 6.0874. Min Act: -0.1700
Data Index: 3424257 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4311. Min Range: -6.4311
Max Act: 6.0561. Min Act: -0.1700
Data Index: 1161760 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4311. Min Range: -6.4311
Max Act: 6.0561. Min Act: -0.1700
Data Index: 6458817 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4311. Min Range: -6.4311
Max Act: 6.0561. Min Act: -0.1700
Data Index: 1537720 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4311. Min Range: -6.4311
Max Act: 6.0561. Min Act: -0.1700
Data Index: 1918994 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4311. Min Range: -6.4311
Max Act: 6.0249. Min Act: -0.1700
Data Index: 8342205 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4311. Min Range: -6.4311
Max Act: 6.0249. Min Act: -0.1700
Data Index: 6695211 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4311. Min Range: -6.4311
Max Act: 5.9936. Min Act: -0.1700
Data Index: 8344974 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4311. Min Range: -6.4311
Max Act: 6.0249. Min Act: -0.1700
Data Index: 3097495 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4311. Min Range: -6.4311
Max Act: 5.9624. Min Act: -0.1700
Data Index: 8014462 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4311. Min Range: -6.4311
Max Act: 5.9624. Min Act: -0.1700
Data Index: 6678273 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4311. Min Range: -6.4311
Max Act: 5.9624. Min Act: -0.1700
Data Index: 585724 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4311. Min Range: -6.4311
Max Act: 5.9624. Min Act: -0.1700
Data Index: 280369 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4311. Min Range: -6.4311
Max Act: 5.9624. Min Act: -0.1700
Data Index: 2645548 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19