Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2019 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8987. Min Range: -4.8987
Max Act: 4.8987. Min Act: -0.1700
Data Index: 4906674 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8987. Min Range: -4.8987
Max Act: 4.8675. Min Act: -0.1700
Data Index: 3384200 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8987. Min Range: -4.8987
Max Act: 4.7425. Min Act: -0.1700
Data Index: 2112909 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8987. Min Range: -4.8987
Max Act: 4.7112. Min Act: -0.1700
Data Index: 2286883 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8987. Min Range: -4.8987
Max Act: 4.7112. Min Act: -0.1700
Data Index: 8729690 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8987. Min Range: -4.8987
Max Act: 4.6800. Min Act: -0.1700
Data Index: 5857730 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8987. Min Range: -4.8987
Max Act: 4.6487. Min Act: -0.1700
Data Index: 643417 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8987. Min Range: -4.8987
Max Act: 4.6487. Min Act: -0.1700
Data Index: 8555784 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8987. Min Range: -4.8987
Max Act: 4.6175. Min Act: -0.1700
Data Index: 5934000 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8987. Min Range: -4.8987
Max Act: 4.5862. Min Act: -0.1700
Data Index: 6244059 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8987. Min Range: -4.8987
Max Act: 4.6175. Min Act: -0.1700
Data Index: 4440677 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8987. Min Range: -4.8987
Max Act: 4.6175. Min Act: -0.1700
Data Index: 5756975 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8987. Min Range: -4.8987
Max Act: 4.5862. Min Act: -0.1700
Data Index: 7833540 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8987. Min Range: -4.8987
Max Act: 4.6175. Min Act: -0.1700
Data Index: 418268 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8987. Min Range: -4.8987
Max Act: 4.5862. Min Act: -0.1700
Data Index: 85050 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8987. Min Range: -4.8987
Max Act: 4.5862. Min Act: -0.1700
Data Index: 351783 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8987. Min Range: -4.8987
Max Act: 4.5862. Min Act: -0.1700
Data Index: 3370202 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8987. Min Range: -4.8987
Max Act: 4.5550. Min Act: -0.1700
Data Index: 3185988 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8987. Min Range: -4.8987
Max Act: 4.5550. Min Act: -0.1700
Data Index: 6741686 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8987. Min Range: -4.8987
Max Act: 4.5862. Min Act: -0.1700
Data Index: 3034832 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19