Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3825 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.8718. Min Range: -0.8718
Max Act: 0.8718. Min Act: -0.1700
Data Index: 2454137 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8718. Min Range: -0.8718
Max Act: 0.8041. Min Act: -0.1676
Data Index: 6758430 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8718. Min Range: -0.8718
Max Act: 0.7957. Min Act: -0.1556
Data Index: 8756466 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8718. Min Range: -0.8718
Max Act: 0.7874. Min Act: -0.1691
Data Index: 6512598 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8718. Min Range: -0.8718
Max Act: 0.7707. Min Act: -0.1700
Data Index: 5510621 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8718. Min Range: -0.8718
Max Act: 0.7624. Min Act: -0.1534
Data Index: 3167051 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8718. Min Range: -0.8718
Max Act: 0.7624. Min Act: -0.1585
Data Index: 4543448 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8718. Min Range: -0.8718
Max Act: 0.7375. Min Act: -0.1697
Data Index: 1592703 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8718. Min Range: -0.8718
Max Act: 0.7458. Min Act: -0.1700
Data Index: 1626068 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8718. Min Range: -0.8718
Max Act: 0.7375. Min Act: -0.1688
Data Index: 5266725 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8718. Min Range: -0.8718
Max Act: 0.7293. Min Act: -0.1700
Data Index: 793458 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8718. Min Range: -0.8718
Max Act: 0.7293. Min Act: -0.1700
Data Index: 5124788 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8718. Min Range: -0.8718
Max Act: 0.7293. Min Act: -0.1690
Data Index: 46446 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8718. Min Range: -0.8718
Max Act: 0.7293. Min Act: -0.1700
Data Index: 1056395 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8718. Min Range: -0.8718
Max Act: 0.7211. Min Act: -0.1700
Data Index: 3477241 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8718. Min Range: -0.8718
Max Act: 0.7293. Min Act: -0.1700
Data Index: 3882668 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8718. Min Range: -0.8718
Max Act: 0.7211. Min Act: -0.1700
Data Index: 1326030 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8718. Min Range: -0.8718
Max Act: 0.7293. Min Act: -0.1698
Data Index: 6142959 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8718. Min Range: -0.8718
Max Act: 0.7047. Min Act: -0.1683
Data Index: 5986057 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8718. Min Range: -0.8718
Max Act: 0.7129. Min Act: -0.1700
Data Index: 6458673 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19