Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3683 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0894. Min Range: -4.0894
Max Act: 4.0894. Min Act: -0.1700
Data Index: 1547878 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0894. Min Range: -4.0894
Max Act: 4.0269. Min Act: -0.1700
Data Index: 5695336 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0894. Min Range: -4.0894
Max Act: 3.9331. Min Act: -0.1700
Data Index: 5695335 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0894. Min Range: -4.0894
Max Act: 3.9331. Min Act: -0.1700
Data Index: 5695338 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0894. Min Range: -4.0894
Max Act: 3.9331. Min Act: -0.1700
Data Index: 5695333 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0894. Min Range: -4.0894
Max Act: 3.9331. Min Act: -0.1700
Data Index: 8409053 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0894. Min Range: -4.0894
Max Act: 3.9331. Min Act: -0.1700
Data Index: 5695341 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0894. Min Range: -4.0894
Max Act: 3.9018. Min Act: -0.1700
Data Index: 1250131 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0894. Min Range: -4.0894
Max Act: 3.9018. Min Act: -0.1700
Data Index: 5695340 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0894. Min Range: -4.0894
Max Act: 3.9018. Min Act: -0.1700
Data Index: 5695331 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0894. Min Range: -4.0894
Max Act: 3.9331. Min Act: -0.1700
Data Index: 5807411 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0894. Min Range: -4.0894
Max Act: 3.9018. Min Act: -0.1700
Data Index: 5695334 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0894. Min Range: -4.0894
Max Act: 3.8705. Min Act: -0.1700
Data Index: 1638853 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0894. Min Range: -4.0894
Max Act: 3.8393. Min Act: -0.1700
Data Index: 5938942 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0894. Min Range: -4.0894
Max Act: 3.8393. Min Act: -0.1700
Data Index: 5695337 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0894. Min Range: -4.0894
Max Act: 3.8080. Min Act: -0.1700
Data Index: 5695332 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0894. Min Range: -4.0894
Max Act: 3.8080. Min Act: -0.1700
Data Index: 5695330 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0894. Min Range: -4.0894
Max Act: 3.8080. Min Act: -0.1700
Data Index: 7545840 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0894. Min Range: -4.0894
Max Act: 3.7767. Min Act: -0.1700
Data Index: 1062952 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0894. Min Range: -4.0894
Max Act: 3.7767. Min Act: -0.1700
Data Index: 1102204 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19