Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4771 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7610. Min Range: -4.7610
Max Act: 4.7610. Min Act: -0.1700
Data Index: 6312860 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7610. Min Range: -4.7610
Max Act: 4.6360. Min Act: -0.1700
Data Index: 33183 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7610. Min Range: -4.7610
Max Act: 4.5735. Min Act: -0.1700
Data Index: 4024880 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7610. Min Range: -4.7610
Max Act: 4.5423. Min Act: -0.1700
Data Index: 1817714 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7610. Min Range: -4.7610
Max Act: 4.5110. Min Act: -0.1700
Data Index: 717039 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7610. Min Range: -4.7610
Max Act: 4.5110. Min Act: -0.1700
Data Index: 5886179 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7610. Min Range: -4.7610
Max Act: 4.4798. Min Act: -0.1700
Data Index: 4404311 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7610. Min Range: -4.7610
Max Act: 4.4173. Min Act: -0.1700
Data Index: 4908713 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7610. Min Range: -4.7610
Max Act: 4.4173. Min Act: -0.1700
Data Index: 5444407 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7610. Min Range: -4.7610
Max Act: 4.4173. Min Act: -0.1700
Data Index: 4434183 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7610. Min Range: -4.7610
Max Act: 4.3860. Min Act: -0.1700
Data Index: 2059656 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7610. Min Range: -4.7610
Max Act: 4.3860. Min Act: -0.1700
Data Index: 4125097 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7610. Min Range: -4.7610
Max Act: 4.3548. Min Act: -0.1700
Data Index: 1019910 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7610. Min Range: -4.7610
Max Act: 4.3548. Min Act: -0.1700
Data Index: 7110877 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7610. Min Range: -4.7610
Max Act: 4.3235. Min Act: -0.1700
Data Index: 1979690 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7610. Min Range: -4.7610
Max Act: 4.3235. Min Act: -0.1700
Data Index: 3273469 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7610. Min Range: -4.7610
Max Act: 4.2923. Min Act: -0.1700
Data Index: 4268715 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7610. Min Range: -4.7610
Max Act: 4.2923. Min Act: -0.1700
Data Index: 2019755 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7610. Min Range: -4.7610
Max Act: 4.2923. Min Act: -0.1700
Data Index: 2006506 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7610. Min Range: -4.7610
Max Act: 4.2923. Min Act: -0.1700
Data Index: 5826147 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19