Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5114 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.8708. Min Act: -0.1700
Data Index: 1991781 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.7458. Min Act: -0.1700
Data Index: 5917485 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.7458. Min Act: -0.1700
Data Index: 6268067 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.7458. Min Act: -0.1700
Data Index: 8088932 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.7146. Min Act: -0.1700
Data Index: 4556628 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.6833. Min Act: -0.1700
Data Index: 1449875 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.6833. Min Act: -0.1700
Data Index: 655196 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.6521. Min Act: -0.1700
Data Index: 7461619 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.6208. Min Act: -0.1700
Data Index: 5938041 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.6208. Min Act: -0.1700
Data Index: 8088933 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.6208. Min Act: -0.1700
Data Index: 8088934 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.5896. Min Act: -0.1700
Data Index: 7449551 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.5583. Min Act: -0.1700
Data Index: 6714074 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.5583. Min Act: -0.1700
Data Index: 4563933 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.5271. Min Act: -0.1700
Data Index: 7490431 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.5271. Min Act: -0.1700
Data Index: 887474 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.4958. Min Act: -0.1700
Data Index: 6766125 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.4646. Min Act: -0.1700
Data Index: 5384741 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.4333. Min Act: -0.1700
Data Index: 960379 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8708. Min Range: -5.8708
Max Act: 5.4333. Min Act: -0.1700
Data Index: 884875 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19