Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5972 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5927. Min Range: -4.5927
Max Act: 4.5927. Min Act: -0.1700
Data Index: 5335136 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5927. Min Range: -4.5927
Max Act: 4.5615. Min Act: -0.1700
Data Index: 6126876 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5927. Min Range: -4.5927
Max Act: 4.5615. Min Act: -0.1700
Data Index: 8620483 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5927. Min Range: -4.5927
Max Act: 4.5927. Min Act: -0.1700
Data Index: 3494837 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5927. Min Range: -4.5927
Max Act: 4.5615. Min Act: -0.1700
Data Index: 7415494 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5927. Min Range: -4.5927
Max Act: 4.5615. Min Act: -0.1700
Data Index: 2966028 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5927. Min Range: -4.5927
Max Act: 4.5615. Min Act: -0.1700
Data Index: 7368558 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5927. Min Range: -4.5927
Max Act: 4.5302. Min Act: -0.1700
Data Index: 921708 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5927. Min Range: -4.5927
Max Act: 4.5615. Min Act: -0.1700
Data Index: 1395445 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5927. Min Range: -4.5927
Max Act: 4.5302. Min Act: -0.1700
Data Index: 728000 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5927. Min Range: -4.5927
Max Act: 4.5302. Min Act: -0.1700
Data Index: 8125140 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5927. Min Range: -4.5927
Max Act: 4.5302. Min Act: -0.1700
Data Index: 8466178 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5927. Min Range: -4.5927
Max Act: 4.5302. Min Act: -0.1700
Data Index: 2874610 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5927. Min Range: -4.5927
Max Act: 4.4990. Min Act: -0.1700
Data Index: 229135 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5927. Min Range: -4.5927
Max Act: 4.4990. Min Act: -0.1700
Data Index: 8554944 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5927. Min Range: -4.5927
Max Act: 4.4677. Min Act: -0.1700
Data Index: 5795473 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5927. Min Range: -4.5927
Max Act: 4.4677. Min Act: -0.1700
Data Index: 199000 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5927. Min Range: -4.5927
Max Act: 4.4677. Min Act: -0.1700
Data Index: 7019495 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5927. Min Range: -4.5927
Max Act: 4.4677. Min Act: -0.1700
Data Index: 7517605 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5927. Min Range: -4.5927
Max Act: 4.4677. Min Act: -0.1700
Data Index: 6848338 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19