Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4823 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4205. Min Range: -9.4205
Max Act: 9.4205. Min Act: -0.1700
Data Index: 4883558 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4205. Min Range: -9.4205
Max Act: 9.1080. Min Act: -0.1700
Data Index: 2982372 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4205. Min Range: -9.4205
Max Act: 8.9830. Min Act: -0.1700
Data Index: 528911 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4205. Min Range: -9.4205
Max Act: 8.9830. Min Act: -0.1700
Data Index: 1006816 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4205. Min Range: -9.4205
Max Act: 8.9830. Min Act: -0.1700
Data Index: 176295 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4205. Min Range: -9.4205
Max Act: 8.9205. Min Act: -0.1700
Data Index: 2046429 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4205. Min Range: -9.4205
Max Act: 8.9205. Min Act: -0.1700
Data Index: 1203212 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4205. Min Range: -9.4205
Max Act: 8.7955. Min Act: -0.1700
Data Index: 6390907 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4205. Min Range: -9.4205
Max Act: 8.7955. Min Act: -0.1700
Data Index: 1231009 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4205. Min Range: -9.4205
Max Act: 8.7330. Min Act: -0.1700
Data Index: 1641717 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4205. Min Range: -9.4205
Max Act: 8.7330. Min Act: -0.1700
Data Index: 810364 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4205. Min Range: -9.4205
Max Act: 8.7330. Min Act: -0.1700
Data Index: 4715180 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4205. Min Range: -9.4205
Max Act: 8.6705. Min Act: -0.1700
Data Index: 8709497 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4205. Min Range: -9.4205
Max Act: 8.6705. Min Act: -0.1700
Data Index: 5098784 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4205. Min Range: -9.4205
Max Act: 8.6080. Min Act: -0.1700
Data Index: 572915 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4205. Min Range: -9.4205
Max Act: 8.6080. Min Act: -0.1700
Data Index: 168980 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4205. Min Range: -9.4205
Max Act: 8.6080. Min Act: -0.1700
Data Index: 1802983 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4205. Min Range: -9.4205
Max Act: 8.6080. Min Act: -0.1700
Data Index: 658348 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4205. Min Range: -9.4205
Max Act: 8.6080. Min Act: -0.1700
Data Index: 8593107 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4205. Min Range: -9.4205
Max Act: 8.5455. Min Act: -0.1700
Data Index: 6397003 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19