Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4590 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9826. Min Range: -8.9826
Max Act: 8.9826. Min Act: -0.1700
Data Index: 7230660 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9826. Min Range: -8.9826
Max Act: 8.8576. Min Act: -0.1700
Data Index: 6220123 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9826. Min Range: -8.9826
Max Act: 8.7951. Min Act: -0.1700
Data Index: 4553140 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9826. Min Range: -8.9826
Max Act: 8.7951. Min Act: -0.1700
Data Index: 610816 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9826. Min Range: -8.9826
Max Act: 8.7951. Min Act: -0.1700
Data Index: 6776663 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9826. Min Range: -8.9826
Max Act: 8.7326. Min Act: -0.1700
Data Index: 1528606 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9826. Min Range: -8.9826
Max Act: 8.6701. Min Act: -0.1700
Data Index: 6776659 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9826. Min Range: -8.9826
Max Act: 8.6076. Min Act: -0.1700
Data Index: 1294893 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9826. Min Range: -8.9826
Max Act: 8.6076. Min Act: -0.1700
Data Index: 532471 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9826. Min Range: -8.9826
Max Act: 8.5451. Min Act: -0.1700
Data Index: 4129164 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9826. Min Range: -8.9826
Max Act: 8.5451. Min Act: -0.1700
Data Index: 7280415 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9826. Min Range: -8.9826
Max Act: 8.4826. Min Act: -0.1700
Data Index: 446367 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9826. Min Range: -8.9826
Max Act: 8.4826. Min Act: -0.1700
Data Index: 7911428 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9826. Min Range: -8.9826
Max Act: 8.4201. Min Act: -0.1700
Data Index: 35944 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9826. Min Range: -8.9826
Max Act: 8.4201. Min Act: -0.1700
Data Index: 1752328 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9826. Min Range: -8.9826
Max Act: 8.4201. Min Act: -0.1700
Data Index: 1613446 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9826. Min Range: -8.9826
Max Act: 8.3576. Min Act: -0.1700
Data Index: 911845 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9826. Min Range: -8.9826
Max Act: 8.3576. Min Act: -0.1700
Data Index: 1450158 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9826. Min Range: -8.9826
Max Act: 8.3576. Min Act: -0.1700
Data Index: 729787 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9826. Min Range: -8.9826
Max Act: 8.2951. Min Act: -0.1700
Data Index: 2823425 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19