Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4285 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1760. Min Range: -5.1760
Max Act: 5.1760. Min Act: -0.1700
Data Index: 72854 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1760. Min Range: -5.1760
Max Act: 5.1448. Min Act: -0.1700
Data Index: 6853423 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1760. Min Range: -5.1760
Max Act: 5.0823. Min Act: -0.1700
Data Index: 5915496 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1760. Min Range: -5.1760
Max Act: 5.0510. Min Act: -0.1700
Data Index: 3299078 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1760. Min Range: -5.1760
Max Act: 5.0510. Min Act: -0.1700
Data Index: 8729304 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1760. Min Range: -5.1760
Max Act: 4.9885. Min Act: -0.1700
Data Index: 7313912 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1760. Min Range: -5.1760
Max Act: 5.0198. Min Act: -0.1700
Data Index: 1913786 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1760. Min Range: -5.1760
Max Act: 4.9885. Min Act: -0.1700
Data Index: 8500633 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1760. Min Range: -5.1760
Max Act: 4.9885. Min Act: -0.1700
Data Index: 6362551 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1760. Min Range: -5.1760
Max Act: 4.9885. Min Act: -0.1700
Data Index: 5241677 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1760. Min Range: -5.1760
Max Act: 4.9260. Min Act: -0.1700
Data Index: 2250536 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1760. Min Range: -5.1760
Max Act: 4.9260. Min Act: -0.1700
Data Index: 8352478 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1760. Min Range: -5.1760
Max Act: 4.9573. Min Act: -0.1700
Data Index: 284894 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1760. Min Range: -5.1760
Max Act: 4.9573. Min Act: -0.1700
Data Index: 4035127 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1760. Min Range: -5.1760
Max Act: 4.9573. Min Act: -0.1700
Data Index: 2850036 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1760. Min Range: -5.1760
Max Act: 4.8948. Min Act: -0.1700
Data Index: 5374262 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1760. Min Range: -5.1760
Max Act: 4.9260. Min Act: -0.1700
Data Index: 2555838 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1760. Min Range: -5.1760
Max Act: 4.9260. Min Act: -0.1700
Data Index: 4951018 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1760. Min Range: -5.1760
Max Act: 4.9260. Min Act: -0.1700
Data Index: 2026551 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1760. Min Range: -5.1760
Max Act: 4.8948. Min Act: -0.1700
Data Index: 1341720 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19