Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3638 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2111. Min Range: -6.2111
Max Act: 6.2111. Min Act: -0.1700
Data Index: 1397280 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2111. Min Range: -6.2111
Max Act: 5.7736. Min Act: -0.1700
Data Index: 6077024 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2111. Min Range: -6.2111
Max Act: 5.6486. Min Act: -0.1700
Data Index: 1670182 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2111. Min Range: -6.2111
Max Act: 5.5861. Min Act: -0.1700
Data Index: 8610981 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2111. Min Range: -6.2111
Max Act: 5.6173. Min Act: -0.1700
Data Index: 7313548 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2111. Min Range: -6.2111
Max Act: 5.4923. Min Act: -0.1700
Data Index: 7852084 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2111. Min Range: -6.2111
Max Act: 5.4611. Min Act: -0.1700
Data Index: 6077043 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2111. Min Range: -6.2111
Max Act: 5.3986. Min Act: -0.1700
Data Index: 3870857 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2111. Min Range: -6.2111
Max Act: 5.3986. Min Act: -0.1700
Data Index: 183710 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2111. Min Range: -6.2111
Max Act: 5.3673. Min Act: -0.1700
Data Index: 8707576 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2111. Min Range: -6.2111
Max Act: 5.3361. Min Act: -0.1700
Data Index: 1462841 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2111. Min Range: -6.2111
Max Act: 5.3673. Min Act: -0.1700
Data Index: 67598 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2111. Min Range: -6.2111
Max Act: 5.3673. Min Act: -0.1700
Data Index: 7072751 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2111. Min Range: -6.2111
Max Act: 5.3673. Min Act: -0.1700
Data Index: 5994267 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2111. Min Range: -6.2111
Max Act: 5.3361. Min Act: -0.1700
Data Index: 1766822 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2111. Min Range: -6.2111
Max Act: 5.3361. Min Act: -0.1700
Data Index: 5994263 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2111. Min Range: -6.2111
Max Act: 5.3048. Min Act: -0.1700
Data Index: 2193428 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2111. Min Range: -6.2111
Max Act: 5.3048. Min Act: -0.1700
Data Index: 1592812 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2111. Min Range: -6.2111
Max Act: 5.2736. Min Act: -0.1700
Data Index: 2184189 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2111. Min Range: -6.2111
Max Act: 5.3048. Min Act: -0.1700
Data Index: 3218253 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19