Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3689 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8805. Min Range: -5.8805
Max Act: 5.8805. Min Act: -0.1700
Data Index: 393727 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8805. Min Range: -5.8805
Max Act: 5.6305. Min Act: -0.1700
Data Index: 283532 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8805. Min Range: -5.8805
Max Act: 5.5993. Min Act: -0.1700
Data Index: 7573290 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8805. Min Range: -5.8805
Max Act: 5.5055. Min Act: -0.1700
Data Index: 5134274 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8805. Min Range: -5.8805
Max Act: 5.4430. Min Act: -0.1700
Data Index: 6147145 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8805. Min Range: -5.8805
Max Act: 5.4430. Min Act: -0.1700
Data Index: 1237417 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8805. Min Range: -5.8805
Max Act: 5.4430. Min Act: -0.1700
Data Index: 1324496 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8805. Min Range: -5.8805
Max Act: 5.4118. Min Act: -0.1700
Data Index: 7424120 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8805. Min Range: -5.8805
Max Act: 5.3805. Min Act: -0.1700
Data Index: 3494323 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8805. Min Range: -5.8805
Max Act: 5.3805. Min Act: -0.1700
Data Index: 8402934 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8805. Min Range: -5.8805
Max Act: 5.3805. Min Act: -0.1700
Data Index: 8402935 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8805. Min Range: -5.8805
Max Act: 5.3805. Min Act: -0.1700
Data Index: 7928447 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8805. Min Range: -5.8805
Max Act: 5.3805. Min Act: -0.1700
Data Index: 3338770 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8805. Min Range: -5.8805
Max Act: 5.3805. Min Act: -0.1700
Data Index: 1978234 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8805. Min Range: -5.8805
Max Act: 5.3493. Min Act: -0.1700
Data Index: 987188 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8805. Min Range: -5.8805
Max Act: 5.3493. Min Act: -0.1700
Data Index: 7877621 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8805. Min Range: -5.8805
Max Act: 5.3493. Min Act: -0.1700
Data Index: 1726016 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8805. Min Range: -5.8805
Max Act: 5.3493. Min Act: -0.1700
Data Index: 4981298 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8805. Min Range: -5.8805
Max Act: 5.3180. Min Act: -0.1700
Data Index: 893656 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8805. Min Range: -5.8805
Max Act: 5.3180. Min Act: -0.1700
Data Index: 5414808 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19