Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3248 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6034. Min Range: -6.6034
Max Act: 6.6034. Min Act: -0.1700
Data Index: 680352 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6034. Min Range: -6.6034
Max Act: 6.6034. Min Act: -0.1700
Data Index: 7134983 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6034. Min Range: -6.6034
Max Act: 6.6034. Min Act: -0.1700
Data Index: 3535515 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6034. Min Range: -6.6034
Max Act: 6.6034. Min Act: -0.1700
Data Index: 2229392 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6034. Min Range: -6.6034
Max Act: 6.5097. Min Act: -0.1700
Data Index: 3098547 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6034. Min Range: -6.6034
Max Act: 6.4784. Min Act: -0.1700
Data Index: 4353172 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6034. Min Range: -6.6034
Max Act: 6.4784. Min Act: -0.1700
Data Index: 1554431 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6034. Min Range: -6.6034
Max Act: 6.4159. Min Act: -0.1700
Data Index: 7299767 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6034. Min Range: -6.6034
Max Act: 6.4159. Min Act: -0.1700
Data Index: 6198132 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6034. Min Range: -6.6034
Max Act: 6.3847. Min Act: -0.1700
Data Index: 2511886 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6034. Min Range: -6.6034
Max Act: 6.4159. Min Act: -0.1700
Data Index: 791529 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6034. Min Range: -6.6034
Max Act: 6.3847. Min Act: -0.1700
Data Index: 4948740 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6034. Min Range: -6.6034
Max Act: 6.3847. Min Act: -0.1700
Data Index: 3508180 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6034. Min Range: -6.6034
Max Act: 6.3847. Min Act: -0.1700
Data Index: 1225288 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6034. Min Range: -6.6034
Max Act: 6.3534. Min Act: -0.1700
Data Index: 5376845 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6034. Min Range: -6.6034
Max Act: 6.3534. Min Act: -0.1700
Data Index: 5879394 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6034. Min Range: -6.6034
Max Act: 6.3534. Min Act: -0.1700
Data Index: 2947654 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6034. Min Range: -6.6034
Max Act: 6.3534. Min Act: -0.1700
Data Index: 5493198 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6034. Min Range: -6.6034
Max Act: 6.3534. Min Act: -0.1700
Data Index: 637787 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6034. Min Range: -6.6034
Max Act: 6.3534. Min Act: -0.1700
Data Index: 6178902 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #19