Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2781 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.9929. Min Act: -0.1700
Data Index: 5438688 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.8367. Min Act: -0.1700
Data Index: 614523 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.8367. Min Act: -0.1700
Data Index: 7746919 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.8367. Min Act: -0.1700
Data Index: 6716075 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.8054. Min Act: -0.1700
Data Index: 3416788 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.7742. Min Act: -0.1700
Data Index: 582809 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.7742. Min Act: -0.1700
Data Index: 3554941 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.7742. Min Act: -0.1700
Data Index: 5518994 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.7429. Min Act: -0.1700
Data Index: 777973 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.7742. Min Act: -0.1700
Data Index: 4035632 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.7117. Min Act: -0.1700
Data Index: 3416789 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.7117. Min Act: -0.1700
Data Index: 7389120 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.7117. Min Act: -0.1700
Data Index: 552666 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.6804. Min Act: -0.1700
Data Index: 894104 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.6179. Min Act: -0.1700
Data Index: 7537438 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.6179. Min Act: -0.1700
Data Index: 2857955 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.6179. Min Act: -0.1700
Data Index: 8670372 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.5867. Min Act: -0.1700
Data Index: 268002 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.5867. Min Act: -0.1700
Data Index: 2812203 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9929. Min Range: -4.9929
Max Act: 4.5867. Min Act: -0.1700
Data Index: 1756685 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19