Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3066 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.8404. Min Range: -0.8404
Max Act: 0.8404. Min Act: -0.1695
Data Index: 902419 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8404. Min Range: -0.8404
Max Act: 0.7401. Min Act: -0.1699
Data Index: 1056058 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8404. Min Range: -0.8404
Max Act: 0.7236. Min Act: -0.1700
Data Index: 8084513 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8404. Min Range: -0.8404
Max Act: 0.7072. Min Act: -0.1700
Data Index: 634978 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8404. Min Range: -0.8404
Max Act: 0.7072. Min Act: -0.1700
Data Index: 3856780 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8404. Min Range: -0.8404
Max Act: 0.6585. Min Act: -0.1700
Data Index: 3963621 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8404. Min Range: -0.8404
Max Act: 0.6425. Min Act: -0.1700
Data Index: 634974 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8404. Min Range: -0.8404
Max Act: 0.6265. Min Act: -0.1700
Data Index: 5594997 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8404. Min Range: -0.8404
Max Act: 0.6265. Min Act: -0.1700
Data Index: 5474773 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8404. Min Range: -0.8404
Max Act: 0.5949. Min Act: -0.1700
Data Index: 5134046 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8404. Min Range: -0.8404
Max Act: 0.5949. Min Act: -0.1699
Data Index: 2596760 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8404. Min Range: -0.8404
Max Act: 0.5949. Min Act: -0.1696
Data Index: 3090334 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8404. Min Range: -0.8404
Max Act: 0.5949. Min Act: -0.1700
Data Index: 4120286 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8404. Min Range: -0.8404
Max Act: 0.5792. Min Act: -0.1700
Data Index: 2969069 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8404. Min Range: -0.8404
Max Act: 0.5637. Min Act: -0.1699
Data Index: 4569518 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8404. Min Range: -0.8404
Max Act: 0.5637. Min Act: -0.1700
Data Index: 7388467 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8404. Min Range: -0.8404
Max Act: 0.5637. Min Act: -0.1700
Data Index: 3955035 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8404. Min Range: -0.8404
Max Act: 0.5637. Min Act: -0.1699
Data Index: 6147889 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8404. Min Range: -0.8404
Max Act: 0.5637. Min Act: -0.1698
Data Index: 3062340 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8404. Min Range: -0.8404
Max Act: 0.5637. Min Act: -0.1685
Data Index: 1041937 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #19