Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3529 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0067. Min Range: -8.0067
Max Act: 8.0067. Min Act: -0.1700
Data Index: 801368 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0067. Min Range: -8.0067
Max Act: 8.0067. Min Act: -0.1700
Data Index: 3614691 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0067. Min Range: -8.0067
Max Act: 8.0067. Min Act: -0.1700
Data Index: 3548802 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0067. Min Range: -8.0067
Max Act: 7.9442. Min Act: -0.1700
Data Index: 876025 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0067. Min Range: -8.0067
Max Act: 7.8505. Min Act: -0.1700
Data Index: 453246 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0067. Min Range: -8.0067
Max Act: 7.8192. Min Act: -0.1700
Data Index: 2639688 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0067. Min Range: -8.0067
Max Act: 7.8192. Min Act: -0.1700
Data Index: 250746 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0067. Min Range: -8.0067
Max Act: 7.8192. Min Act: -0.1700
Data Index: 3075692 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0067. Min Range: -8.0067
Max Act: 7.7880. Min Act: -0.1700
Data Index: 6172986 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0067. Min Range: -8.0067
Max Act: 7.7567. Min Act: -0.1700
Data Index: 6723769 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0067. Min Range: -8.0067
Max Act: 7.7567. Min Act: -0.1700
Data Index: 4974229 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0067. Min Range: -8.0067
Max Act: 7.7255. Min Act: -0.1700
Data Index: 892860 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0067. Min Range: -8.0067
Max Act: 7.7255. Min Act: -0.1700
Data Index: 7971553 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0067. Min Range: -8.0067
Max Act: 7.6630. Min Act: -0.1700
Data Index: 5932074 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0067. Min Range: -8.0067
Max Act: 7.7255. Min Act: -0.1700
Data Index: 5451928 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0067. Min Range: -8.0067
Max Act: 7.6630. Min Act: -0.1700
Data Index: 6855028 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0067. Min Range: -8.0067
Max Act: 7.6317. Min Act: -0.1700
Data Index: 6923785 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0067. Min Range: -8.0067
Max Act: 7.6317. Min Act: -0.1700
Data Index: 3026147 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0067. Min Range: -8.0067
Max Act: 7.5692. Min Act: -0.1700
Data Index: 5569007 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0067. Min Range: -8.0067
Max Act: 7.5692. Min Act: -0.1700
Data Index: 163518 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19