Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1728 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3211. Min Range: -7.3211
Max Act: 7.3211. Min Act: -0.1700
Data Index: 4560734 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3211. Min Range: -7.3211
Max Act: 7.1961. Min Act: -0.1700
Data Index: 5649216 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3211. Min Range: -7.3211
Max Act: 7.1961. Min Act: -0.1700
Data Index: 6862590 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3211. Min Range: -7.3211
Max Act: 7.1961. Min Act: -0.1700
Data Index: 4570936 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3211. Min Range: -7.3211
Max Act: 7.1024. Min Act: -0.1700
Data Index: 578430 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3211. Min Range: -7.3211
Max Act: 7.1024. Min Act: -0.1700
Data Index: 8290606 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3211. Min Range: -7.3211
Max Act: 7.1024. Min Act: -0.1700
Data Index: 5077607 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3211. Min Range: -7.3211
Max Act: 7.0711. Min Act: -0.1700
Data Index: 2016635 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3211. Min Range: -7.3211
Max Act: 7.0711. Min Act: -0.1693
Data Index: 6900661 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3211. Min Range: -7.3211
Max Act: 7.0399. Min Act: -0.1700
Data Index: 4863994 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3211. Min Range: -7.3211
Max Act: 7.0399. Min Act: -0.1700
Data Index: 1688870 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3211. Min Range: -7.3211
Max Act: 7.0086. Min Act: -0.1700
Data Index: 5743750 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3211. Min Range: -7.3211
Max Act: 7.0086. Min Act: -0.1699
Data Index: 2497109 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3211. Min Range: -7.3211
Max Act: 7.0086. Min Act: -0.1700
Data Index: 2431347 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3211. Min Range: -7.3211
Max Act: 6.9774. Min Act: -0.1700
Data Index: 1469131 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3211. Min Range: -7.3211
Max Act: 6.9774. Min Act: -0.1700
Data Index: 4228962 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3211. Min Range: -7.3211
Max Act: 6.9461. Min Act: -0.1700
Data Index: 3823689 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3211. Min Range: -7.3211
Max Act: 6.9774. Min Act: -0.1700
Data Index: 1163674 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3211. Min Range: -7.3211
Max Act: 6.9774. Min Act: -0.1700
Data Index: 5461289 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3211. Min Range: -7.3211
Max Act: 6.9774. Min Act: -0.1700
Data Index: 1219318 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19