Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2541 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7723. Min Range: -6.7723
Max Act: 6.7723. Min Act: -0.1700
Data Index: 3354992 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7723. Min Range: -6.7723
Max Act: 6.4910. Min Act: -0.1700
Data Index: 6912234 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7723. Min Range: -6.7723
Max Act: 6.3973. Min Act: -0.1700
Data Index: 6763259 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7723. Min Range: -6.7723
Max Act: 6.3035. Min Act: -0.1700
Data Index: 7338485 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7723. Min Range: -6.7723
Max Act: 6.2723. Min Act: -0.1700
Data Index: 2635859 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7723. Min Range: -6.7723
Max Act: 6.2098. Min Act: -0.1700
Data Index: 2263350 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7723. Min Range: -6.7723
Max Act: 6.2098. Min Act: -0.1700
Data Index: 3492697 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7723. Min Range: -6.7723
Max Act: 6.1785. Min Act: -0.1700
Data Index: 2643488 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7723. Min Range: -6.7723
Max Act: 6.1785. Min Act: -0.1700
Data Index: 4977856 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7723. Min Range: -6.7723
Max Act: 6.1473. Min Act: -0.1700
Data Index: 7983670 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7723. Min Range: -6.7723
Max Act: 6.1473. Min Act: -0.1700
Data Index: 5756134 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7723. Min Range: -6.7723
Max Act: 6.1473. Min Act: -0.1700
Data Index: 7688323 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7723. Min Range: -6.7723
Max Act: 6.1160. Min Act: -0.1700
Data Index: 7718801 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7723. Min Range: -6.7723
Max Act: 6.1160. Min Act: -0.1700
Data Index: 1138479 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7723. Min Range: -6.7723
Max Act: 6.1160. Min Act: -0.1700
Data Index: 2884568 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7723. Min Range: -6.7723
Max Act: 6.1473. Min Act: -0.1700
Data Index: 5490395 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7723. Min Range: -6.7723
Max Act: 6.0848. Min Act: -0.1700
Data Index: 3503154 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7723. Min Range: -6.7723
Max Act: 6.0848. Min Act: -0.1700
Data Index: 1720229 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7723. Min Range: -6.7723
Max Act: 6.0848. Min Act: -0.1700
Data Index: 6834275 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7723. Min Range: -6.7723
Max Act: 6.0848. Min Act: -0.1700
Data Index: 8703266 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19