Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3772 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9535. Min Range: -5.9535
Max Act: 5.9535. Min Act: -0.1700
Data Index: 8799622 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9535. Min Range: -5.9535
Max Act: 5.8910. Min Act: -0.1700
Data Index: 7828317 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9535. Min Range: -5.9535
Max Act: 5.8910. Min Act: -0.1700
Data Index: 8327208 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9535. Min Range: -5.9535
Max Act: 5.8910. Min Act: -0.1700
Data Index: 3858366 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9535. Min Range: -5.9535
Max Act: 5.8598. Min Act: -0.1700
Data Index: 4513888 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9535. Min Range: -5.9535
Max Act: 5.8598. Min Act: -0.1700
Data Index: 3411874 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9535. Min Range: -5.9535
Max Act: 5.8285. Min Act: -0.1700
Data Index: 7963820 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9535. Min Range: -5.9535
Max Act: 5.8285. Min Act: -0.1700
Data Index: 1091565 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9535. Min Range: -5.9535
Max Act: 5.7660. Min Act: -0.1700
Data Index: 5596729 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9535. Min Range: -5.9535
Max Act: 5.7973. Min Act: -0.1700
Data Index: 4012139 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9535. Min Range: -5.9535
Max Act: 5.7660. Min Act: -0.1700
Data Index: 5921839 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9535. Min Range: -5.9535
Max Act: 5.7348. Min Act: -0.1700
Data Index: 5067891 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9535. Min Range: -5.9535
Max Act: 5.7348. Min Act: -0.1700
Data Index: 4306254 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9535. Min Range: -5.9535
Max Act: 5.7035. Min Act: -0.1700
Data Index: 1852331 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9535. Min Range: -5.9535
Max Act: 5.7035. Min Act: -0.1700
Data Index: 7215957 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9535. Min Range: -5.9535
Max Act: 5.6723. Min Act: -0.1700
Data Index: 2233669 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9535. Min Range: -5.9535
Max Act: 5.6723. Min Act: -0.1700
Data Index: 4533849 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9535. Min Range: -5.9535
Max Act: 5.6723. Min Act: -0.1700
Data Index: 4858694 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9535. Min Range: -5.9535
Max Act: 5.6723. Min Act: -0.1700
Data Index: 6861062 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9535. Min Range: -5.9535
Max Act: 5.6410. Min Act: -0.1700
Data Index: 4619991 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19