Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3316 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9883. Min Range: -6.9883
Max Act: 6.9883. Min Act: -0.1700
Data Index: 1170009 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9883. Min Range: -6.9883
Max Act: 6.9570. Min Act: -0.1700
Data Index: 5773932 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9883. Min Range: -6.9883
Max Act: 6.8633. Min Act: -0.1700
Data Index: 937825 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9883. Min Range: -6.9883
Max Act: 6.8008. Min Act: -0.1700
Data Index: 8629555 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9883. Min Range: -6.9883
Max Act: 6.8008. Min Act: -0.1700
Data Index: 8639340 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9883. Min Range: -6.9883
Max Act: 6.8008. Min Act: -0.1700
Data Index: 4524384 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9883. Min Range: -6.9883
Max Act: 6.8008. Min Act: -0.1700
Data Index: 6211422 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9883. Min Range: -6.9883
Max Act: 6.8008. Min Act: -0.1700
Data Index: 3335739 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9883. Min Range: -6.9883
Max Act: 6.8008. Min Act: -0.1700
Data Index: 8160068 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9883. Min Range: -6.9883
Max Act: 6.8008. Min Act: -0.1700
Data Index: 6437008 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9883. Min Range: -6.9883
Max Act: 6.7695. Min Act: -0.1700
Data Index: 4733367 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9883. Min Range: -6.9883
Max Act: 6.7695. Min Act: -0.1700
Data Index: 1230085 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9883. Min Range: -6.9883
Max Act: 6.7695. Min Act: -0.1700
Data Index: 6683453 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9883. Min Range: -6.9883
Max Act: 6.7383. Min Act: -0.1700
Data Index: 2587866 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9883. Min Range: -6.9883
Max Act: 6.7383. Min Act: -0.1700
Data Index: 7046617 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9883. Min Range: -6.9883
Max Act: 6.7383. Min Act: -0.1700
Data Index: 441145 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9883. Min Range: -6.9883
Max Act: 6.7383. Min Act: -0.1700
Data Index: 8365118 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9883. Min Range: -6.9883
Max Act: 6.6758. Min Act: -0.1700
Data Index: 102203 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9883. Min Range: -6.9883
Max Act: 6.7070. Min Act: -0.1700
Data Index: 907641 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9883. Min Range: -6.9883
Max Act: 6.6758. Min Act: -0.1700
Data Index: 4900551 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19