Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2785 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5924. Min Range: -8.5924
Max Act: 8.5924. Min Act: -0.1700
Data Index: 7598800 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5924. Min Range: -8.5924
Max Act: 8.4049. Min Act: -0.1700
Data Index: 4712728 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5924. Min Range: -8.5924
Max Act: 8.2799. Min Act: -0.1700
Data Index: 1932445 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5924. Min Range: -8.5924
Max Act: 8.2174. Min Act: -0.1700
Data Index: 7998945 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5924. Min Range: -8.5924
Max Act: 8.1549. Min Act: -0.1700
Data Index: 2617046 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5924. Min Range: -8.5924
Max Act: 8.0299. Min Act: -0.1700
Data Index: 4585080 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5924. Min Range: -8.5924
Max Act: 7.9674. Min Act: -0.1700
Data Index: 7041878 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5924. Min Range: -8.5924
Max Act: 7.9674. Min Act: -0.1700
Data Index: 4822779 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5924. Min Range: -8.5924
Max Act: 7.9674. Min Act: -0.1700
Data Index: 1729694 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5924. Min Range: -8.5924
Max Act: 7.9674. Min Act: -0.1700
Data Index: 6418327 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5924. Min Range: -8.5924
Max Act: 7.8424. Min Act: -0.1700
Data Index: 8109967 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5924. Min Range: -8.5924
Max Act: 7.9049. Min Act: -0.1700
Data Index: 353387 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5924. Min Range: -8.5924
Max Act: 7.8424. Min Act: -0.1700
Data Index: 1562933 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5924. Min Range: -8.5924
Max Act: 7.8424. Min Act: -0.1700
Data Index: 1425695 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5924. Min Range: -8.5924
Max Act: 7.7799. Min Act: -0.1700
Data Index: 3010668 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5924. Min Range: -8.5924
Max Act: 7.8424. Min Act: -0.1700
Data Index: 4795966 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5924. Min Range: -8.5924
Max Act: 7.7799. Min Act: -0.1700
Data Index: 3309804 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5924. Min Range: -8.5924
Max Act: 7.7799. Min Act: -0.1700
Data Index: 8250073 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5924. Min Range: -8.5924
Max Act: 7.7799. Min Act: -0.1700
Data Index: 3481748 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5924. Min Range: -8.5924
Max Act: 7.7174. Min Act: -0.1700
Data Index: 6957515 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19