Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2867 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2863. Min Range: -6.2863
Max Act: 6.2863. Min Act: -0.1700
Data Index: 3917125 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2863. Min Range: -6.2863
Max Act: 6.0363. Min Act: -0.1700
Data Index: 2332236 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2863. Min Range: -6.2863
Max Act: 5.9738. Min Act: -0.1700
Data Index: 7763739 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2863. Min Range: -6.2863
Max Act: 5.9425. Min Act: -0.1700
Data Index: 7564405 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2863. Min Range: -6.2863
Max Act: 5.8175. Min Act: -0.1700
Data Index: 1148143 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2863. Min Range: -6.2863
Max Act: 5.7863. Min Act: -0.1700
Data Index: 1149831 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2863. Min Range: -6.2863
Max Act: 5.7863. Min Act: -0.1700
Data Index: 895023 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2863. Min Range: -6.2863
Max Act: 5.7550. Min Act: -0.1700
Data Index: 8246333 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2863. Min Range: -6.2863
Max Act: 5.7550. Min Act: -0.1700
Data Index: 4638423 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2863. Min Range: -6.2863
Max Act: 5.7238. Min Act: -0.1700
Data Index: 2111131 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2863. Min Range: -6.2863
Max Act: 5.7238. Min Act: -0.1700
Data Index: 4413787 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2863. Min Range: -6.2863
Max Act: 5.6613. Min Act: -0.1700
Data Index: 7375267 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2863. Min Range: -6.2863
Max Act: 5.6300. Min Act: -0.1700
Data Index: 4041034 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2863. Min Range: -6.2863
Max Act: 5.6300. Min Act: -0.1700
Data Index: 3689986 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2863. Min Range: -6.2863
Max Act: 5.6300. Min Act: -0.1700
Data Index: 3756256 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2863. Min Range: -6.2863
Max Act: 5.6300. Min Act: -0.1700
Data Index: 4926279 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2863. Min Range: -6.2863
Max Act: 5.6300. Min Act: -0.1700
Data Index: 4423070 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2863. Min Range: -6.2863
Max Act: 5.6300. Min Act: -0.1700
Data Index: 8219947 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2863. Min Range: -6.2863
Max Act: 5.6300. Min Act: -0.1700
Data Index: 8514069 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2863. Min Range: -6.2863
Max Act: 5.5988. Min Act: -0.1700
Data Index: 7811735 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19