Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5927 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6618. Min Range: -6.6618
Max Act: 6.6618. Min Act: -0.1700
Data Index: 8128604 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6618. Min Range: -6.6618
Max Act: 6.5680. Min Act: -0.1700
Data Index: 8709481 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6618. Min Range: -6.6618
Max Act: 6.5055. Min Act: -0.1700
Data Index: 1057250 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6618. Min Range: -6.6618
Max Act: 6.4118. Min Act: -0.1700
Data Index: 5008660 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6618. Min Range: -6.6618
Max Act: 6.3493. Min Act: -0.1700
Data Index: 4708220 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6618. Min Range: -6.6618
Max Act: 6.2243. Min Act: -0.1700
Data Index: 1378842 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6618. Min Range: -6.6618
Max Act: 6.1618. Min Act: -0.1700
Data Index: 5473713 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6618. Min Range: -6.6618
Max Act: 6.1305. Min Act: -0.1700
Data Index: 3316393 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6618. Min Range: -6.6618
Max Act: 6.0993. Min Act: -0.1700
Data Index: 8415041 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6618. Min Range: -6.6618
Max Act: 6.1305. Min Act: -0.1700
Data Index: 6269751 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6618. Min Range: -6.6618
Max Act: 6.1305. Min Act: -0.1700
Data Index: 7835845 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6618. Min Range: -6.6618
Max Act: 6.0993. Min Act: -0.1700
Data Index: 8274898 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6618. Min Range: -6.6618
Max Act: 6.0993. Min Act: -0.1700
Data Index: 1010666 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6618. Min Range: -6.6618
Max Act: 6.0993. Min Act: -0.1700
Data Index: 755450 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6618. Min Range: -6.6618
Max Act: 6.0680. Min Act: -0.1700
Data Index: 4578493 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6618. Min Range: -6.6618
Max Act: 6.0680. Min Act: -0.1700
Data Index: 1978154 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6618. Min Range: -6.6618
Max Act: 6.0368. Min Act: -0.1700
Data Index: 76847 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6618. Min Range: -6.6618
Max Act: 6.0368. Min Act: -0.1700
Data Index: 5323081 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6618. Min Range: -6.6618
Max Act: 6.0368. Min Act: -0.1700
Data Index: 3069567 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6618. Min Range: -6.6618
Max Act: 6.0055. Min Act: -0.1700
Data Index: 5491132 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19