Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2608 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8907. Min Range: -5.8907
Max Act: 5.8907. Min Act: -0.1700
Data Index: 1587444 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8907. Min Range: -5.8907
Max Act: 5.8907. Min Act: -0.1700
Data Index: 6591027 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8907. Min Range: -5.8907
Max Act: 5.8282. Min Act: -0.1700
Data Index: 2621891 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8907. Min Range: -5.8907
Max Act: 5.8282. Min Act: -0.1700
Data Index: 5913173 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8907. Min Range: -5.8907
Max Act: 5.7657. Min Act: -0.1700
Data Index: 377779 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8907. Min Range: -5.8907
Max Act: 5.6407. Min Act: -0.1700
Data Index: 3258699 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8907. Min Range: -5.8907
Max Act: 5.6407. Min Act: -0.1700
Data Index: 2206607 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8907. Min Range: -5.8907
Max Act: 5.6720. Min Act: -0.1700
Data Index: 3792840 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8907. Min Range: -5.8907
Max Act: 5.6720. Min Act: -0.1700
Data Index: 6464257 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8907. Min Range: -5.8907
Max Act: 5.6720. Min Act: -0.1700
Data Index: 6165342 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8907. Min Range: -5.8907
Max Act: 5.6720. Min Act: -0.1700
Data Index: 6296164 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8907. Min Range: -5.8907
Max Act: 5.6407. Min Act: -0.1700
Data Index: 3156545 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8907. Min Range: -5.8907
Max Act: 5.6407. Min Act: -0.1700
Data Index: 400061 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8907. Min Range: -5.8907
Max Act: 5.6407. Min Act: -0.1700
Data Index: 7534517 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8907. Min Range: -5.8907
Max Act: 5.6095. Min Act: -0.1700
Data Index: 2372257 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8907. Min Range: -5.8907
Max Act: 5.6095. Min Act: -0.1700
Data Index: 7237995 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8907. Min Range: -5.8907
Max Act: 5.6095. Min Act: -0.1700
Data Index: 4640742 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8907. Min Range: -5.8907
Max Act: 5.5782. Min Act: -0.1700
Data Index: 377780 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8907. Min Range: -5.8907
Max Act: 5.5782. Min Act: -0.1700
Data Index: 2713048 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8907. Min Range: -5.8907
Max Act: 5.5782. Min Act: -0.1700
Data Index: 4958079 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19