Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6041 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7024. Min Range: -6.7024
Max Act: 6.7024. Min Act: -0.1700
Data Index: 7478511 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7024. Min Range: -6.7024
Max Act: 6.1711. Min Act: -0.1700
Data Index: 3224286 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7024. Min Range: -6.7024
Max Act: 6.1399. Min Act: -0.1700
Data Index: 7051543 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7024. Min Range: -6.7024
Max Act: 6.1086. Min Act: -0.1700
Data Index: 6439911 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7024. Min Range: -6.7024
Max Act: 6.0774. Min Act: -0.1700
Data Index: 237271 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7024. Min Range: -6.7024
Max Act: 6.0774. Min Act: -0.1700
Data Index: 783086 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7024. Min Range: -6.7024
Max Act: 6.0461. Min Act: -0.1700
Data Index: 8189043 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7024. Min Range: -6.7024
Max Act: 6.0461. Min Act: -0.1700
Data Index: 4160633 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7024. Min Range: -6.7024
Max Act: 6.0149. Min Act: -0.1700
Data Index: 2097767 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7024. Min Range: -6.7024
Max Act: 5.9524. Min Act: -0.1700
Data Index: 3742595 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7024. Min Range: -6.7024
Max Act: 5.9524. Min Act: -0.1700
Data Index: 7814912 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7024. Min Range: -6.7024
Max Act: 5.9524. Min Act: -0.1700
Data Index: 1453578 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7024. Min Range: -6.7024
Max Act: 5.9524. Min Act: -0.1700
Data Index: 1342165 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7024. Min Range: -6.7024
Max Act: 5.9524. Min Act: -0.1700
Data Index: 5836695 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7024. Min Range: -6.7024
Max Act: 5.9836. Min Act: -0.1700
Data Index: 3237513 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7024. Min Range: -6.7024
Max Act: 5.9524. Min Act: -0.1700
Data Index: 7188768 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7024. Min Range: -6.7024
Max Act: 5.9524. Min Act: -0.1700
Data Index: 1561178 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7024. Min Range: -6.7024
Max Act: 5.9211. Min Act: -0.1700
Data Index: 6762856 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7024. Min Range: -6.7024
Max Act: 5.9211. Min Act: -0.1700
Data Index: 5989428 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7024. Min Range: -6.7024
Max Act: 5.8899. Min Act: -0.1700
Data Index: 1238729 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19