Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3832 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4923. Min Range: -6.4923
Max Act: 6.4923. Min Act: -0.1700
Data Index: 249240 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4923. Min Range: -6.4923
Max Act: 6.3360. Min Act: -0.1700
Data Index: 3403727 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4923. Min Range: -6.4923
Max Act: 6.2423. Min Act: -0.1700
Data Index: 3776070 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4923. Min Range: -6.4923
Max Act: 6.2110. Min Act: -0.1700
Data Index: 7748107 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4923. Min Range: -6.4923
Max Act: 6.2110. Min Act: -0.1700
Data Index: 1947417 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4923. Min Range: -6.4923
Max Act: 6.0860. Min Act: -0.1700
Data Index: 4171246 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4923. Min Range: -6.4923
Max Act: 6.0235. Min Act: -0.1700
Data Index: 7317422 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4923. Min Range: -6.4923
Max Act: 5.9923. Min Act: -0.1700
Data Index: 5165517 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4923. Min Range: -6.4923
Max Act: 5.9923. Min Act: -0.1700
Data Index: 5245070 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4923. Min Range: -6.4923
Max Act: 5.9610. Min Act: -0.1700
Data Index: 709483 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4923. Min Range: -6.4923
Max Act: 5.8985. Min Act: -0.1700
Data Index: 4344780 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4923. Min Range: -6.4923
Max Act: 5.9298. Min Act: -0.1700
Data Index: 6360366 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4923. Min Range: -6.4923
Max Act: 5.9298. Min Act: -0.1700
Data Index: 3423502 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4923. Min Range: -6.4923
Max Act: 5.9298. Min Act: -0.1700
Data Index: 648756 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4923. Min Range: -6.4923
Max Act: 5.9298. Min Act: -0.1700
Data Index: 6150437 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4923. Min Range: -6.4923
Max Act: 5.9298. Min Act: -0.1700
Data Index: 2040691 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4923. Min Range: -6.4923
Max Act: 5.8985. Min Act: -0.1700
Data Index: 8831020 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4923. Min Range: -6.4923
Max Act: 5.8985. Min Act: -0.1700
Data Index: 6838583 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4923. Min Range: -6.4923
Max Act: 5.9298. Min Act: -0.1700
Data Index: 2520039 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4923. Min Range: -6.4923
Max Act: 5.8673. Min Act: -0.1700
Data Index: 1943772 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19