Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1704 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5205. Min Range: -5.5205
Max Act: 5.5205. Min Act: -0.1698
Data Index: 263692 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5205. Min Range: -5.5205
Max Act: 5.4892. Min Act: -0.1700
Data Index: 417321 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5205. Min Range: -5.5205
Max Act: 5.4892. Min Act: -0.1699
Data Index: 2649720 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5205. Min Range: -5.5205
Max Act: 5.4580. Min Act: -0.1700
Data Index: 203612 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5205. Min Range: -5.5205
Max Act: 5.4580. Min Act: -0.1678
Data Index: 2371810 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5205. Min Range: -5.5205
Max Act: 5.4580. Min Act: -0.1698
Data Index: 8127414 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5205. Min Range: -5.5205
Max Act: 5.4580. Min Act: -0.1700
Data Index: 8747817 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5205. Min Range: -5.5205
Max Act: 5.4580. Min Act: -0.1700
Data Index: 59531 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5205. Min Range: -5.5205
Max Act: 5.4580. Min Act: -0.1700
Data Index: 658964 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5205. Min Range: -5.5205
Max Act: 5.4267. Min Act: -0.1700
Data Index: 7030852 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5205. Min Range: -5.5205
Max Act: 5.3955. Min Act: -0.1699
Data Index: 6219907 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5205. Min Range: -5.5205
Max Act: 5.3955. Min Act: -0.1700
Data Index: 770764 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5205. Min Range: -5.5205
Max Act: 5.4267. Min Act: -0.1700
Data Index: 1698211 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5205. Min Range: -5.5205
Max Act: 5.4580. Min Act: -0.1696
Data Index: 553659 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5205. Min Range: -5.5205
Max Act: 5.4267. Min Act: -0.1700
Data Index: 5216976 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5205. Min Range: -5.5205
Max Act: 5.4267. Min Act: -0.1700
Data Index: 8178831 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5205. Min Range: -5.5205
Max Act: 5.3955. Min Act: -0.1700
Data Index: 367358 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5205. Min Range: -5.5205
Max Act: 5.3642. Min Act: -0.1698
Data Index: 3494535 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5205. Min Range: -5.5205
Max Act: 5.3955. Min Act: -0.1700
Data Index: 6009254 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5205. Min Range: -5.5205
Max Act: 5.3955. Min Act: -0.1700
Data Index: 263690 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19