Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4640 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.6236. Min Range: -8.6236
Max Act: 8.6236. Min Act: -0.1700
Data Index: 3194746 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6236. Min Range: -8.6236
Max Act: 8.6236. Min Act: -0.1700
Data Index: 4430091 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6236. Min Range: -8.6236
Max Act: 8.6236. Min Act: -0.1700
Data Index: 2167818 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6236. Min Range: -8.6236
Max Act: 8.5611. Min Act: -0.1700
Data Index: 7152813 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6236. Min Range: -8.6236
Max Act: 8.5611. Min Act: -0.1700
Data Index: 4223192 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6236. Min Range: -8.6236
Max Act: 8.5611. Min Act: -0.1700
Data Index: 3986729 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6236. Min Range: -8.6236
Max Act: 8.4986. Min Act: -0.1700
Data Index: 2226737 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6236. Min Range: -8.6236
Max Act: 8.4986. Min Act: -0.1700
Data Index: 595035 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6236. Min Range: -8.6236
Max Act: 8.4986. Min Act: -0.1700
Data Index: 1873071 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6236. Min Range: -8.6236
Max Act: 8.4361. Min Act: -0.1700
Data Index: 3954686 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6236. Min Range: -8.6236
Max Act: 8.3736. Min Act: -0.1700
Data Index: 1974443 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6236. Min Range: -8.6236
Max Act: 8.4361. Min Act: -0.1700
Data Index: 8182477 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6236. Min Range: -8.6236
Max Act: 8.4361. Min Act: -0.1700
Data Index: 4923272 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6236. Min Range: -8.6236
Max Act: 8.4361. Min Act: -0.1700
Data Index: 5487853 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6236. Min Range: -8.6236
Max Act: 8.3736. Min Act: -0.1700
Data Index: 4363613 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6236. Min Range: -8.6236
Max Act: 8.3736. Min Act: -0.1700
Data Index: 4187163 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6236. Min Range: -8.6236
Max Act: 8.3736. Min Act: -0.1700
Data Index: 3810876 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6236. Min Range: -8.6236
Max Act: 8.3736. Min Act: -0.1700
Data Index: 2573045 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6236. Min Range: -8.6236
Max Act: 8.3736. Min Act: -0.1700
Data Index: 4905530 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6236. Min Range: -8.6236
Max Act: 8.3736. Min Act: -0.1700
Data Index: 4675705 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19