Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3162 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8045. Min Range: -7.8045
Max Act: 7.8045. Min Act: -0.1700
Data Index: 4029534 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8045. Min Range: -7.8045
Max Act: 7.6795. Min Act: -0.1700
Data Index: 7845257 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8045. Min Range: -7.8045
Max Act: 7.6795. Min Act: -0.1700
Data Index: 7833951 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8045. Min Range: -7.8045
Max Act: 7.5232. Min Act: -0.1700
Data Index: 2198299 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8045. Min Range: -7.8045
Max Act: 7.4295. Min Act: -0.1700
Data Index: 6545225 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8045. Min Range: -7.8045
Max Act: 7.4295. Min Act: -0.1700
Data Index: 5765009 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8045. Min Range: -7.8045
Max Act: 7.4295. Min Act: -0.1700
Data Index: 5924107 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8045. Min Range: -7.8045
Max Act: 7.3357. Min Act: -0.1700
Data Index: 2661263 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8045. Min Range: -7.8045
Max Act: 7.3357. Min Act: -0.1700
Data Index: 1553494 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8045. Min Range: -7.8045
Max Act: 7.2732. Min Act: -0.1700
Data Index: 6838800 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8045. Min Range: -7.8045
Max Act: 7.2732. Min Act: -0.1700
Data Index: 3373799 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8045. Min Range: -7.8045
Max Act: 7.2732. Min Act: -0.1700
Data Index: 785399 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8045. Min Range: -7.8045
Max Act: 7.2420. Min Act: -0.1700
Data Index: 5387510 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8045. Min Range: -7.8045
Max Act: 7.1170. Min Act: -0.1700
Data Index: 1416913 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8045. Min Range: -7.8045
Max Act: 7.1482. Min Act: -0.1700
Data Index: 6237803 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8045. Min Range: -7.8045
Max Act: 7.1170. Min Act: -0.1700
Data Index: 1938314 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8045. Min Range: -7.8045
Max Act: 7.0857. Min Act: -0.1700
Data Index: 2541878 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8045. Min Range: -7.8045
Max Act: 7.0857. Min Act: -0.1700
Data Index: 5793579 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8045. Min Range: -7.8045
Max Act: 7.1170. Min Act: -0.1700
Data Index: 6244815 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8045. Min Range: -7.8045
Max Act: 7.0545. Min Act: -0.1700
Data Index: 6669870 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #19