Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2811 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9071. Min Range: -5.9071
Max Act: 5.9071. Min Act: -0.1700
Data Index: 8439602 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9071. Min Range: -5.9071
Max Act: 5.5008. Min Act: -0.1700
Data Index: 3049009 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9071. Min Range: -5.9071
Max Act: 5.5008. Min Act: -0.1700
Data Index: 6435780 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9071. Min Range: -5.9071
Max Act: 5.5008. Min Act: -0.1700
Data Index: 5170047 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9071. Min Range: -5.9071
Max Act: 5.5008. Min Act: -0.1700
Data Index: 4401609 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9071. Min Range: -5.9071
Max Act: 5.5008. Min Act: -0.1700
Data Index: 2982247 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9071. Min Range: -5.9071
Max Act: 5.5008. Min Act: -0.1700
Data Index: 1907162 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9071. Min Range: -5.9071
Max Act: 5.5008. Min Act: -0.1700
Data Index: 5609644 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9071. Min Range: -5.9071
Max Act: 5.4696. Min Act: -0.1700
Data Index: 2729992 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9071. Min Range: -5.9071
Max Act: 5.4383. Min Act: -0.1700
Data Index: 5415017 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9071. Min Range: -5.9071
Max Act: 5.4383. Min Act: -0.1700
Data Index: 3883425 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9071. Min Range: -5.9071
Max Act: 5.4383. Min Act: -0.1700
Data Index: 240765 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9071. Min Range: -5.9071
Max Act: 5.4071. Min Act: -0.1700
Data Index: 1114153 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9071. Min Range: -5.9071
Max Act: 5.3758. Min Act: -0.1700
Data Index: 5547861 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9071. Min Range: -5.9071
Max Act: 5.3758. Min Act: -0.1700
Data Index: 2832246 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9071. Min Range: -5.9071
Max Act: 5.3446. Min Act: -0.1700
Data Index: 6797218 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9071. Min Range: -5.9071
Max Act: 5.3446. Min Act: -0.1700
Data Index: 2272516 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9071. Min Range: -5.9071
Max Act: 5.3446. Min Act: -0.1700
Data Index: 6327695 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9071. Min Range: -5.9071
Max Act: 5.3446. Min Act: -0.1700
Data Index: 1383998 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9071. Min Range: -5.9071
Max Act: 5.3446. Min Act: -0.1700
Data Index: 2449834 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19