Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 85 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6714. Min Range: -4.6714
Max Act: 4.6714. Min Act: -0.1700
Data Index: 600593 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6714. Min Range: -4.6714
Max Act: 4.6401. Min Act: -0.1700
Data Index: 5994844 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6714. Min Range: -4.6714
Max Act: 4.6401. Min Act: -0.1700
Data Index: 3967574 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6714. Min Range: -4.6714
Max Act: 4.6401. Min Act: -0.1700
Data Index: 459341 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6714. Min Range: -4.6714
Max Act: 4.5776. Min Act: -0.1700
Data Index: 4382010 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6714. Min Range: -4.6714
Max Act: 4.6089. Min Act: -0.1700
Data Index: 370838 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6714. Min Range: -4.6714
Max Act: 4.6089. Min Act: -0.1700
Data Index: 2650215 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6714. Min Range: -4.6714
Max Act: 4.6089. Min Act: -0.1700
Data Index: 3013633 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6714. Min Range: -4.6714
Max Act: 4.5776. Min Act: -0.1700
Data Index: 4960635 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6714. Min Range: -4.6714
Max Act: 4.5776. Min Act: -0.1700
Data Index: 8750247 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6714. Min Range: -4.6714
Max Act: 4.5151. Min Act: -0.1700
Data Index: 3369735 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6714. Min Range: -4.6714
Max Act: 4.5151. Min Act: -0.1700
Data Index: 6557171 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6714. Min Range: -4.6714
Max Act: 4.5151. Min Act: -0.1700
Data Index: 8706697 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6714. Min Range: -4.6714
Max Act: 4.5151. Min Act: -0.1700
Data Index: 2556648 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6714. Min Range: -4.6714
Max Act: 4.5151. Min Act: -0.1700
Data Index: 2492922 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6714. Min Range: -4.6714
Max Act: 4.5151. Min Act: -0.1700
Data Index: 6368930 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6714. Min Range: -4.6714
Max Act: 4.4526. Min Act: -0.1700
Data Index: 7688703 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6714. Min Range: -4.6714
Max Act: 4.4526. Min Act: -0.1700
Data Index: 8434463 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6714. Min Range: -4.6714
Max Act: 4.5151. Min Act: -0.1700
Data Index: 4181078 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6714. Min Range: -4.6714
Max Act: 4.4839. Min Act: -0.1700
Data Index: 1213244 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19