Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3048 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1861. Min Range: -8.1861
Max Act: 8.1861. Min Act: -0.1700
Data Index: 3286990 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1861. Min Range: -8.1861
Max Act: 8.0611. Min Act: -0.1700
Data Index: 5601125 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1861. Min Range: -8.1861
Max Act: 7.9049. Min Act: -0.1700
Data Index: 8535995 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1861. Min Range: -8.1861
Max Act: 7.8424. Min Act: -0.1700
Data Index: 8132234 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1861. Min Range: -8.1861
Max Act: 7.8424. Min Act: -0.1700
Data Index: 108853 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1861. Min Range: -8.1861
Max Act: 7.7174. Min Act: -0.1700
Data Index: 494444 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1861. Min Range: -8.1861
Max Act: 7.6549. Min Act: -0.1700
Data Index: 2012099 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1861. Min Range: -8.1861
Max Act: 7.6861. Min Act: -0.1700
Data Index: 7229028 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1861. Min Range: -8.1861
Max Act: 7.6549. Min Act: -0.1700
Data Index: 6661400 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1861. Min Range: -8.1861
Max Act: 7.6236. Min Act: -0.1700
Data Index: 4525732 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1861. Min Range: -8.1861
Max Act: 7.6236. Min Act: -0.1700
Data Index: 2322528 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1861. Min Range: -8.1861
Max Act: 7.5299. Min Act: -0.1700
Data Index: 120841 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1861. Min Range: -8.1861
Max Act: 7.5299. Min Act: -0.1700
Data Index: 2203398 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1861. Min Range: -8.1861
Max Act: 7.4986. Min Act: -0.1700
Data Index: 8375218 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1861. Min Range: -8.1861
Max Act: 7.4674. Min Act: -0.1700
Data Index: 5883684 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1861. Min Range: -8.1861
Max Act: 7.4674. Min Act: -0.1700
Data Index: 7667622 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1861. Min Range: -8.1861
Max Act: 7.3424. Min Act: -0.1700
Data Index: 1618850 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1861. Min Range: -8.1861
Max Act: 7.3736. Min Act: -0.1700
Data Index: 7164815 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1861. Min Range: -8.1861
Max Act: 7.3424. Min Act: -0.1700
Data Index: 505180 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1861. Min Range: -8.1861
Max Act: 7.4049. Min Act: -0.1700
Data Index: 6396081 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19