Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2845 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6602. Min Range: -6.6602
Max Act: 6.6602. Min Act: -0.1700
Data Index: 8360314 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6602. Min Range: -6.6602
Max Act: 6.6602. Min Act: -0.1700
Data Index: 732212 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6602. Min Range: -6.6602
Max Act: 6.6602. Min Act: -0.1700
Data Index: 3261867 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6602. Min Range: -6.6602
Max Act: 6.5977. Min Act: -0.1700
Data Index: 4153948 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6602. Min Range: -6.6602
Max Act: 6.5352. Min Act: -0.1700
Data Index: 6326740 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6602. Min Range: -6.6602
Max Act: 6.5039. Min Act: -0.1700
Data Index: 438558 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6602. Min Range: -6.6602
Max Act: 6.4727. Min Act: -0.1700
Data Index: 8509804 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6602. Min Range: -6.6602
Max Act: 6.4727. Min Act: -0.1700
Data Index: 5503210 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6602. Min Range: -6.6602
Max Act: 6.4102. Min Act: -0.1700
Data Index: 1648665 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6602. Min Range: -6.6602
Max Act: 6.4102. Min Act: -0.1700
Data Index: 4376561 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6602. Min Range: -6.6602
Max Act: 6.4102. Min Act: -0.1700
Data Index: 3137120 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6602. Min Range: -6.6602
Max Act: 6.4102. Min Act: -0.1700
Data Index: 1091718 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6602. Min Range: -6.6602
Max Act: 6.4102. Min Act: -0.1700
Data Index: 7689816 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6602. Min Range: -6.6602
Max Act: 6.4102. Min Act: -0.1700
Data Index: 4795940 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6602. Min Range: -6.6602
Max Act: 6.3789. Min Act: -0.1700
Data Index: 776193 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6602. Min Range: -6.6602
Max Act: 6.3477. Min Act: -0.1700
Data Index: 6540291 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6602. Min Range: -6.6602
Max Act: 6.3477. Min Act: -0.1700
Data Index: 6740628 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6602. Min Range: -6.6602
Max Act: 6.3477. Min Act: -0.1700
Data Index: 5289461 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6602. Min Range: -6.6602
Max Act: 6.3789. Min Act: -0.1700
Data Index: 5849198 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6602. Min Range: -6.6602
Max Act: 6.2852. Min Act: -0.1700
Data Index: 1707008 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19