Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3655 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6926. Min Range: -6.6926
Max Act: 6.6926. Min Act: -0.1700
Data Index: 5204060 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6926. Min Range: -6.6926
Max Act: 6.6301. Min Act: -0.1700
Data Index: 6895469 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6926. Min Range: -6.6926
Max Act: 6.4426. Min Act: -0.1700
Data Index: 6957984 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6926. Min Range: -6.6926
Max Act: 6.3801. Min Act: -0.1700
Data Index: 3422387 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6926. Min Range: -6.6926
Max Act: 6.2238. Min Act: -0.1700
Data Index: 3269668 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6926. Min Range: -6.6926
Max Act: 6.1613. Min Act: -0.1700
Data Index: 5103821 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6926. Min Range: -6.6926
Max Act: 6.1613. Min Act: -0.1700
Data Index: 4308743 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6926. Min Range: -6.6926
Max Act: 6.0988. Min Act: -0.1700
Data Index: 3609560 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6926. Min Range: -6.6926
Max Act: 6.0988. Min Act: -0.1700
Data Index: 7103737 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6926. Min Range: -6.6926
Max Act: 6.1301. Min Act: -0.1700
Data Index: 6813308 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6926. Min Range: -6.6926
Max Act: 6.0988. Min Act: -0.1700
Data Index: 8542699 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6926. Min Range: -6.6926
Max Act: 6.0676. Min Act: -0.1700
Data Index: 2175126 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6926. Min Range: -6.6926
Max Act: 6.0988. Min Act: -0.1700
Data Index: 6201147 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6926. Min Range: -6.6926
Max Act: 6.0676. Min Act: -0.1700
Data Index: 4696512 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6926. Min Range: -6.6926
Max Act: 6.0363. Min Act: -0.1700
Data Index: 6858219 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6926. Min Range: -6.6926
Max Act: 6.0676. Min Act: -0.1700
Data Index: 4723105 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6926. Min Range: -6.6926
Max Act: 6.0363. Min Act: -0.1700
Data Index: 2920268 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6926. Min Range: -6.6926
Max Act: 6.0363. Min Act: -0.1700
Data Index: 3562431 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6926. Min Range: -6.6926
Max Act: 6.0051. Min Act: -0.1700
Data Index: 6201157 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6926. Min Range: -6.6926
Max Act: 5.9738. Min Act: -0.1700
Data Index: 2725777 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19