Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3635 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3989. Min Range: -6.3989
Max Act: 6.3989. Min Act: -0.1700
Data Index: 7066466 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3989. Min Range: -6.3989
Max Act: 6.3676. Min Act: -0.1700
Data Index: 2450647 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3989. Min Range: -6.3989
Max Act: 6.3364. Min Act: -0.1700
Data Index: 8619959 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3989. Min Range: -6.3989
Max Act: 6.3051. Min Act: -0.1700
Data Index: 609769 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3989. Min Range: -6.3989
Max Act: 6.3051. Min Act: -0.1699
Data Index: 3858495 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3989. Min Range: -6.3989
Max Act: 6.2426. Min Act: -0.1700
Data Index: 6710425 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3989. Min Range: -6.3989
Max Act: 6.1801. Min Act: -0.1700
Data Index: 6402214 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3989. Min Range: -6.3989
Max Act: 6.2114. Min Act: -0.1700
Data Index: 6490675 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3989. Min Range: -6.3989
Max Act: 6.1489. Min Act: -0.1700
Data Index: 8485639 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3989. Min Range: -6.3989
Max Act: 6.1176. Min Act: -0.1700
Data Index: 2563980 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3989. Min Range: -6.3989
Max Act: 6.1489. Min Act: -0.1700
Data Index: 1462397 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3989. Min Range: -6.3989
Max Act: 6.0864. Min Act: -0.1700
Data Index: 738139 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3989. Min Range: -6.3989
Max Act: 6.0864. Min Act: -0.1700
Data Index: 4496701 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3989. Min Range: -6.3989
Max Act: 6.0239. Min Act: -0.1700
Data Index: 7161998 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3989. Min Range: -6.3989
Max Act: 6.0551. Min Act: -0.1700
Data Index: 919126 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3989. Min Range: -6.3989
Max Act: 5.9926. Min Act: -0.1700
Data Index: 3422170 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3989. Min Range: -6.3989
Max Act: 5.9926. Min Act: -0.1700
Data Index: 53091 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3989. Min Range: -6.3989
Max Act: 5.9926. Min Act: -0.1700
Data Index: 6129941 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3989. Min Range: -6.3989
Max Act: 5.9926. Min Act: -0.1700
Data Index: 3030311 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3989. Min Range: -6.3989
Max Act: 5.9926. Min Act: -0.1700
Data Index: 6869935 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19