Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3477 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3324. Min Range: -9.3324
Max Act: 9.3324. Min Act: -0.1700
Data Index: 7658195 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3324. Min Range: -9.3324
Max Act: 9.0824. Min Act: -0.1700
Data Index: 3569500 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3324. Min Range: -9.3324
Max Act: 9.0199. Min Act: -0.1700
Data Index: 766905 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3324. Min Range: -9.3324
Max Act: 8.8324. Min Act: -0.1700
Data Index: 2201196 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3324. Min Range: -9.3324
Max Act: 8.7699. Min Act: -0.1700
Data Index: 3026607 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3324. Min Range: -9.3324
Max Act: 8.7074. Min Act: -0.1700
Data Index: 5679442 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3324. Min Range: -9.3324
Max Act: 8.6449. Min Act: -0.1700
Data Index: 5775278 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3324. Min Range: -9.3324
Max Act: 8.6449. Min Act: -0.1700
Data Index: 7778627 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3324. Min Range: -9.3324
Max Act: 8.5824. Min Act: -0.1700
Data Index: 1011889 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3324. Min Range: -9.3324
Max Act: 8.5199. Min Act: -0.1700
Data Index: 5668205 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3324. Min Range: -9.3324
Max Act: 8.5824. Min Act: -0.1700
Data Index: 3716914 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3324. Min Range: -9.3324
Max Act: 8.5824. Min Act: -0.1700
Data Index: 1881709 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3324. Min Range: -9.3324
Max Act: 8.5824. Min Act: -0.1700
Data Index: 6866283 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3324. Min Range: -9.3324
Max Act: 8.5824. Min Act: -0.1700
Data Index: 5551874 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3324. Min Range: -9.3324
Max Act: 8.5824. Min Act: -0.1700
Data Index: 3757954 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3324. Min Range: -9.3324
Max Act: 8.5199. Min Act: -0.1700
Data Index: 933152 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3324. Min Range: -9.3324
Max Act: 8.5824. Min Act: -0.1700
Data Index: 931840 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3324. Min Range: -9.3324
Max Act: 8.5199. Min Act: -0.1700
Data Index: 7683032 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3324. Min Range: -9.3324
Max Act: 8.4574. Min Act: -0.1700
Data Index: 555774 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3324. Min Range: -9.3324
Max Act: 8.4574. Min Act: -0.1700
Data Index: 6800313 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19