Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3194 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2581. Min Range: -9.2581
Max Act: 9.2581. Min Act: -0.1700
Data Index: 3378102 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2581. Min Range: -9.2581
Max Act: 9.1331. Min Act: -0.1700
Data Index: 8560244 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2581. Min Range: -9.2581
Max Act: 8.8831. Min Act: -0.1700
Data Index: 5468991 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2581. Min Range: -9.2581
Max Act: 8.8206. Min Act: -0.1700
Data Index: 8270889 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2581. Min Range: -9.2581
Max Act: 8.7581. Min Act: -0.1700
Data Index: 8316444 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2581. Min Range: -9.2581
Max Act: 8.6956. Min Act: -0.1700
Data Index: 7870484 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2581. Min Range: -9.2581
Max Act: 8.6956. Min Act: -0.1700
Data Index: 8484861 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2581. Min Range: -9.2581
Max Act: 8.6956. Min Act: -0.1700
Data Index: 8128923 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2581. Min Range: -9.2581
Max Act: 8.7581. Min Act: -0.1700
Data Index: 3378118 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2581. Min Range: -9.2581
Max Act: 8.6956. Min Act: -0.1700
Data Index: 8128937 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2581. Min Range: -9.2581
Max Act: 8.6956. Min Act: -0.1700
Data Index: 535328 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2581. Min Range: -9.2581
Max Act: 8.6331. Min Act: -0.1700
Data Index: 347801 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2581. Min Range: -9.2581
Max Act: 8.6331. Min Act: -0.1700
Data Index: 8216206 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2581. Min Range: -9.2581
Max Act: 8.6331. Min Act: -0.1700
Data Index: 6648656 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2581. Min Range: -9.2581
Max Act: 8.6331. Min Act: -0.1700
Data Index: 5830955 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2581. Min Range: -9.2581
Max Act: 8.6331. Min Act: -0.1700
Data Index: 8190832 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2581. Min Range: -9.2581
Max Act: 8.6331. Min Act: -0.1700
Data Index: 6757702 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2581. Min Range: -9.2581
Max Act: 8.5706. Min Act: -0.1700
Data Index: 5469010 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2581. Min Range: -9.2581
Max Act: 8.5706. Min Act: -0.1700
Data Index: 3794311 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2581. Min Range: -9.2581
Max Act: 8.5706. Min Act: -0.1700
Data Index: 3560448 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19