Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 536 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6284. Min Range: -5.6284
Max Act: 5.6284. Min Act: -0.1700
Data Index: 4109749 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6284. Min Range: -5.6284
Max Act: 5.5659. Min Act: -0.1700
Data Index: 8135046 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6284. Min Range: -5.6284
Max Act: 5.5347. Min Act: -0.1700
Data Index: 3491809 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6284. Min Range: -5.6284
Max Act: 5.5347. Min Act: -0.1700
Data Index: 4705466 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6284. Min Range: -5.6284
Max Act: 5.5034. Min Act: -0.1700
Data Index: 5852835 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6284. Min Range: -5.6284
Max Act: 5.4409. Min Act: -0.1700
Data Index: 6831316 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6284. Min Range: -5.6284
Max Act: 5.4722. Min Act: -0.1700
Data Index: 5989812 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6284. Min Range: -5.6284
Max Act: 5.4722. Min Act: -0.1700
Data Index: 2380137 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6284. Min Range: -5.6284
Max Act: 5.4409. Min Act: -0.1700
Data Index: 8206818 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6284. Min Range: -5.6284
Max Act: 5.4409. Min Act: -0.1700
Data Index: 6950936 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6284. Min Range: -5.6284
Max Act: 5.4409. Min Act: -0.1700
Data Index: 2386352 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6284. Min Range: -5.6284
Max Act: 5.4097. Min Act: -0.1700
Data Index: 3155685 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6284. Min Range: -5.6284
Max Act: 5.4409. Min Act: -0.1700
Data Index: 2972372 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6284. Min Range: -5.6284
Max Act: 5.4097. Min Act: -0.1700
Data Index: 5349891 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6284. Min Range: -5.6284
Max Act: 5.4097. Min Act: -0.1700
Data Index: 905873 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6284. Min Range: -5.6284
Max Act: 5.3784. Min Act: -0.1700
Data Index: 3286687 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6284. Min Range: -5.6284
Max Act: 5.3784. Min Act: -0.1700
Data Index: 1056329 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6284. Min Range: -5.6284
Max Act: 5.3784. Min Act: -0.1700
Data Index: 459593 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6284. Min Range: -5.6284
Max Act: 5.3784. Min Act: -0.1700
Data Index: 1564188 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6284. Min Range: -5.6284
Max Act: 5.3784. Min Act: -0.1700
Data Index: 1793906 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19