Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3273 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5839. Min Range: -5.5839
Max Act: 5.5839. Min Act: -0.1700
Data Index: 6779197 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5839. Min Range: -5.5839
Max Act: 5.5526. Min Act: -0.1700
Data Index: 4115237 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5839. Min Range: -5.5839
Max Act: 5.5214. Min Act: -0.1700
Data Index: 5564326 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5839. Min Range: -5.5839
Max Act: 5.4901. Min Act: -0.1700
Data Index: 4251931 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5839. Min Range: -5.5839
Max Act: 5.4901. Min Act: -0.1700
Data Index: 3600366 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5839. Min Range: -5.5839
Max Act: 5.4276. Min Act: -0.1700
Data Index: 3173824 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5839. Min Range: -5.5839
Max Act: 5.4276. Min Act: -0.1700
Data Index: 6986721 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5839. Min Range: -5.5839
Max Act: 5.3964. Min Act: -0.1700
Data Index: 8169001 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5839. Min Range: -5.5839
Max Act: 5.3964. Min Act: -0.1700
Data Index: 5848913 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5839. Min Range: -5.5839
Max Act: 5.3964. Min Act: -0.1700
Data Index: 4390123 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5839. Min Range: -5.5839
Max Act: 5.3339. Min Act: -0.1700
Data Index: 6498425 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5839. Min Range: -5.5839
Max Act: 5.3651. Min Act: -0.1700
Data Index: 6336879 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5839. Min Range: -5.5839
Max Act: 5.3339. Min Act: -0.1700
Data Index: 6994688 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5839. Min Range: -5.5839
Max Act: 5.3339. Min Act: -0.1700
Data Index: 7390477 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5839. Min Range: -5.5839
Max Act: 5.3339. Min Act: -0.1700
Data Index: 4734805 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5839. Min Range: -5.5839
Max Act: 5.3339. Min Act: -0.1700
Data Index: 3462926 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5839. Min Range: -5.5839
Max Act: 5.3026. Min Act: -0.1700
Data Index: 4058149 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5839. Min Range: -5.5839
Max Act: 5.3026. Min Act: -0.1700
Data Index: 7528581 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5839. Min Range: -5.5839
Max Act: 5.3339. Min Act: -0.1696
Data Index: 4335162 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5839. Min Range: -5.5839
Max Act: 5.3026. Min Act: -0.1700
Data Index: 3236167 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19