Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3395 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0451. Min Range: -8.0451
Max Act: 8.0451. Min Act: -0.1700
Data Index: 4180105 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0451. Min Range: -8.0451
Max Act: 8.0451. Min Act: -0.1700
Data Index: 1612863 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0451. Min Range: -8.0451
Max Act: 7.9826. Min Act: -0.1700
Data Index: 1126604 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0451. Min Range: -8.0451
Max Act: 8.0451. Min Act: -0.1700
Data Index: 4721750 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0451. Min Range: -8.0451
Max Act: 7.9201. Min Act: -0.1700
Data Index: 8336985 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0451. Min Range: -8.0451
Max Act: 7.8576. Min Act: -0.1700
Data Index: 792875 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0451. Min Range: -8.0451
Max Act: 7.7951. Min Act: -0.1700
Data Index: 5083356 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0451. Min Range: -8.0451
Max Act: 7.7951. Min Act: -0.1700
Data Index: 496000 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0451. Min Range: -8.0451
Max Act: 7.7951. Min Act: -0.1700
Data Index: 5432961 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0451. Min Range: -8.0451
Max Act: 7.7951. Min Act: -0.1700
Data Index: 6760369 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0451. Min Range: -8.0451
Max Act: 7.7326. Min Act: -0.1700
Data Index: 4429649 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0451. Min Range: -8.0451
Max Act: 7.7326. Min Act: -0.1700
Data Index: 3650583 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0451. Min Range: -8.0451
Max Act: 7.7326. Min Act: -0.1700
Data Index: 3118551 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0451. Min Range: -8.0451
Max Act: 7.7326. Min Act: -0.1700
Data Index: 5789891 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0451. Min Range: -8.0451
Max Act: 7.7326. Min Act: -0.1700
Data Index: 269600 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0451. Min Range: -8.0451
Max Act: 7.7326. Min Act: -0.1700
Data Index: 1554678 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0451. Min Range: -8.0451
Max Act: 7.7326. Min Act: -0.1700
Data Index: 5574828 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0451. Min Range: -8.0451
Max Act: 7.7326. Min Act: -0.1700
Data Index: 3155320 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0451. Min Range: -8.0451
Max Act: 7.7326. Min Act: -0.1700
Data Index: 78151 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0451. Min Range: -8.0451
Max Act: 7.7326. Min Act: -0.1700
Data Index: 1111477 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19