Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1506 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.4933. Min Act: -0.1700
Data Index: 3553211 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.4620. Min Act: -0.1700
Data Index: 6395342 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.4308. Min Act: -0.1700
Data Index: 628679 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.4308. Min Act: -0.1700
Data Index: 7230246 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.4308. Min Act: -0.1700
Data Index: 7336970 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.3995. Min Act: -0.1700
Data Index: 118437 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.4308. Min Act: -0.1700
Data Index: 406944 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.4620. Min Act: -0.1700
Data Index: 2433904 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.3995. Min Act: -0.1700
Data Index: 6395339 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.4308. Min Act: -0.1700
Data Index: 6514518 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.3370. Min Act: -0.1700
Data Index: 2199269 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.3370. Min Act: -0.1700
Data Index: 993674 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.3370. Min Act: -0.1700
Data Index: 6771235 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.3370. Min Act: -0.1700
Data Index: 2562627 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.3058. Min Act: -0.1700
Data Index: 5822875 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.3058. Min Act: -0.1700
Data Index: 4462359 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.3058. Min Act: -0.1700
Data Index: 8121657 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.3370. Min Act: -0.1700
Data Index: 1658860 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.3370. Min Act: -0.1700
Data Index: 3442908 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4933. Min Range: -4.4933
Max Act: 4.2745. Min Act: -0.1700
Data Index: 1221956 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19