Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3332 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.3692. Min Act: -0.1700
Data Index: 5808875 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.1817. Min Act: -0.1700
Data Index: 4282091 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.0879. Min Act: -0.1700
Data Index: 3519062 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.0567. Min Act: -0.1700
Data Index: 1393025 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3692. Min Range: -6.3692
Max Act: 6.0567. Min Act: -0.1700
Data Index: 3587430 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.9942. Min Act: -0.1700
Data Index: 3822674 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.9942. Min Act: -0.1700
Data Index: 5947091 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.9317. Min Act: -0.1700
Data Index: 7500782 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.9317. Min Act: -0.1700
Data Index: 8095309 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.8692. Min Act: -0.1700
Data Index: 5600461 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.9004. Min Act: -0.1700
Data Index: 6471448 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.8692. Min Act: -0.1700
Data Index: 73181 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.9004. Min Act: -0.1700
Data Index: 5291574 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.8692. Min Act: -0.1700
Data Index: 8316444 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.8379. Min Act: -0.1700
Data Index: 8706093 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.8379. Min Act: -0.1700
Data Index: 1362147 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.8379. Min Act: -0.1700
Data Index: 3265331 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.8067. Min Act: -0.1700
Data Index: 3557885 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.8067. Min Act: -0.1700
Data Index: 755285 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3692. Min Range: -6.3692
Max Act: 5.8379. Min Act: -0.1700
Data Index: 1508169 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19