Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3110 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7024. Min Range: -3.7024
Max Act: 3.7024. Min Act: -0.1700
Data Index: 6946397 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7024. Min Range: -3.7024
Max Act: 3.6555. Min Act: -0.1700
Data Index: 5460811 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7024. Min Range: -3.7024
Max Act: 3.6085. Min Act: -0.1700
Data Index: 3975991 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7024. Min Range: -3.7024
Max Act: 3.5772. Min Act: -0.1700
Data Index: 3810019 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7024. Min Range: -3.7024
Max Act: 3.5616. Min Act: -0.1700
Data Index: 6246746 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7024. Min Range: -3.7024
Max Act: 3.5146. Min Act: -0.1700
Data Index: 963521 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7024. Min Range: -3.7024
Max Act: 3.5459. Min Act: -0.1700
Data Index: 7214017 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7024. Min Range: -3.7024
Max Act: 3.4989. Min Act: -0.1700
Data Index: 3252633 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7024. Min Range: -3.7024
Max Act: 3.4833. Min Act: -0.1700
Data Index: 3530838 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7024. Min Range: -3.7024
Max Act: 3.4833. Min Act: -0.1700
Data Index: 6074546 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7024. Min Range: -3.7024
Max Act: 3.4833. Min Act: -0.1700
Data Index: 2230724 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7024. Min Range: -3.7024
Max Act: 3.4676. Min Act: -0.1700
Data Index: 75121 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7024. Min Range: -3.7024
Max Act: 3.4519. Min Act: -0.1700
Data Index: 6160234 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7024. Min Range: -3.7024
Max Act: 3.4363. Min Act: -0.1700
Data Index: 7665048 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7024. Min Range: -3.7024
Max Act: 3.3892. Min Act: -0.1700
Data Index: 421219 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7024. Min Range: -3.7024
Max Act: 3.4049. Min Act: -0.1700
Data Index: 6775460 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7024. Min Range: -3.7024
Max Act: 3.3892. Min Act: -0.1700
Data Index: 6624178 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7024. Min Range: -3.7024
Max Act: 3.3736. Min Act: -0.1700
Data Index: 1169505 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7024. Min Range: -3.7024
Max Act: 3.3892. Min Act: -0.1700
Data Index: 5577622 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7024. Min Range: -3.7024
Max Act: 3.3736. Min Act: -0.1700
Data Index: 1817732 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19