Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2900 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0039. Min Range: -6.0039
Max Act: 6.0039. Min Act: -0.1700
Data Index: 4720294 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0039. Min Range: -6.0039
Max Act: 5.9726. Min Act: -0.1700
Data Index: 2695646 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0039. Min Range: -6.0039
Max Act: 5.9414. Min Act: -0.1700
Data Index: 1003521 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0039. Min Range: -6.0039
Max Act: 5.9101. Min Act: -0.1700
Data Index: 2109143 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0039. Min Range: -6.0039
Max Act: 5.8476. Min Act: -0.1700
Data Index: 2662188 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0039. Min Range: -6.0039
Max Act: 5.8164. Min Act: -0.1700
Data Index: 4722992 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0039. Min Range: -6.0039
Max Act: 5.8164. Min Act: -0.1700
Data Index: 2607488 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0039. Min Range: -6.0039
Max Act: 5.7851. Min Act: -0.1700
Data Index: 2950704 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0039. Min Range: -6.0039
Max Act: 5.7851. Min Act: -0.1700
Data Index: 1529523 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0039. Min Range: -6.0039
Max Act: 5.7851. Min Act: -0.1700
Data Index: 6322833 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0039. Min Range: -6.0039
Max Act: 5.7539. Min Act: -0.1700
Data Index: 8255814 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0039. Min Range: -6.0039
Max Act: 5.6914. Min Act: -0.1700
Data Index: 1838662 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0039. Min Range: -6.0039
Max Act: 5.6914. Min Act: -0.1700
Data Index: 2227497 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0039. Min Range: -6.0039
Max Act: 5.6601. Min Act: -0.1700
Data Index: 3913189 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0039. Min Range: -6.0039
Max Act: 5.6289. Min Act: -0.1700
Data Index: 5491166 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0039. Min Range: -6.0039
Max Act: 5.6289. Min Act: -0.1700
Data Index: 7028003 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0039. Min Range: -6.0039
Max Act: 5.5976. Min Act: -0.1700
Data Index: 1105795 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0039. Min Range: -6.0039
Max Act: 5.6289. Min Act: -0.1700
Data Index: 1368828 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0039. Min Range: -6.0039
Max Act: 5.5976. Min Act: -0.1700
Data Index: 5796181 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0039. Min Range: -6.0039
Max Act: 5.5664. Min Act: -0.1700
Data Index: 1838664 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19