Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3937 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6979. Min Range: -2.6979
Max Act: 2.6818. Min Act: -0.1700
Data Index: 7487750 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6979. Min Range: -2.6979
Max Act: 2.6979. Min Act: -0.1700
Data Index: 4206679 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6979. Min Range: -2.6979
Max Act: 2.6498. Min Act: -0.1700
Data Index: 3560083 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6979. Min Range: -2.6979
Max Act: 2.6177. Min Act: -0.1700
Data Index: 3234097 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6979. Min Range: -2.6979
Max Act: 2.6016. Min Act: -0.1700
Data Index: 7248982 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6979. Min Range: -2.6979
Max Act: 2.6016. Min Act: -0.1700
Data Index: 5789790 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6979. Min Range: -2.6979
Max Act: 2.5855. Min Act: -0.1700
Data Index: 6625445 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6979. Min Range: -2.6979
Max Act: 2.5693. Min Act: -0.1700
Data Index: 8776729 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6979. Min Range: -2.6979
Max Act: 2.5855. Min Act: -0.1700
Data Index: 1015202 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6979. Min Range: -2.6979
Max Act: 2.5693. Min Act: -0.1700
Data Index: 7366042 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6979. Min Range: -2.6979
Max Act: 2.5855. Min Act: -0.1700
Data Index: 5817850 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6979. Min Range: -2.6979
Max Act: 2.5532. Min Act: -0.1700
Data Index: 5236872 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6979. Min Range: -2.6979
Max Act: 2.5532. Min Act: -0.1700
Data Index: 492236 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6979. Min Range: -2.6979
Max Act: 2.5371. Min Act: -0.1700
Data Index: 4280319 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6979. Min Range: -2.6979
Max Act: 2.5532. Min Act: -0.1700
Data Index: 2668500 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6979. Min Range: -2.6979
Max Act: 2.5532. Min Act: -0.1700
Data Index: 2609951 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6979. Min Range: -2.6979
Max Act: 2.5532. Min Act: -0.1700
Data Index: 8019818 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6979. Min Range: -2.6979
Max Act: 2.5532. Min Act: -0.1700
Data Index: 7932730 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6979. Min Range: -2.6979
Max Act: 2.5371. Min Act: -0.1700
Data Index: 3070853 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6979. Min Range: -2.6979
Max Act: 2.5532. Min Act: -0.1700
Data Index: 6817800 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19