Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3410 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.2048. Min Range: -12.2048
Max Act: 12.2048. Min Act: -0.1700
Data Index: 3643032 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.2048. Min Range: -12.2048
Max Act: 12.2048. Min Act: -0.1700
Data Index: 2081345 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.2048. Min Range: -12.2048
Max Act: 12.2048. Min Act: -0.1700
Data Index: 719620 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.2048. Min Range: -12.2048
Max Act: 12.1423. Min Act: -0.1700
Data Index: 2945318 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.2048. Min Range: -12.2048
Max Act: 12.0798. Min Act: -0.1700
Data Index: 5255642 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.2048. Min Range: -12.2048
Max Act: 12.0798. Min Act: -0.1700
Data Index: 6620921 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.2048. Min Range: -12.2048
Max Act: 12.0173. Min Act: -0.1700
Data Index: 2221154 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.2048. Min Range: -12.2048
Max Act: 12.0173. Min Act: -0.1700
Data Index: 3569958 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.2048. Min Range: -12.2048
Max Act: 12.0173. Min Act: -0.1700
Data Index: 709659 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.2048. Min Range: -12.2048
Max Act: 11.9548. Min Act: -0.1700
Data Index: 8298421 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.2048. Min Range: -12.2048
Max Act: 11.8923. Min Act: -0.1700
Data Index: 5683461 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.2048. Min Range: -12.2048
Max Act: 11.8923. Min Act: -0.1700
Data Index: 1860018 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.2048. Min Range: -12.2048
Max Act: 11.8923. Min Act: -0.1700
Data Index: 2081342 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.2048. Min Range: -12.2048
Max Act: 11.8923. Min Act: -0.1700
Data Index: 2965265 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.2048. Min Range: -12.2048
Max Act: 11.8923. Min Act: -0.1700
Data Index: 6729182 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.2048. Min Range: -12.2048
Max Act: 11.8923. Min Act: -0.1700
Data Index: 694791 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.2048. Min Range: -12.2048
Max Act: 11.8298. Min Act: -0.1700
Data Index: 4158891 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.2048. Min Range: -12.2048
Max Act: 11.8298. Min Act: -0.1700
Data Index: 1669060 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.2048. Min Range: -12.2048
Max Act: 11.8298. Min Act: -0.1700
Data Index: 2768668 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.2048. Min Range: -12.2048
Max Act: 11.8298. Min Act: -0.1700
Data Index: 5528675 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19