Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3169 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.8673. Min Range: -13.8673
Max Act: 13.8673. Min Act: -0.1700
Data Index: 7688908 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.8673. Min Range: -13.8673
Max Act: 13.6798. Min Act: -0.1700
Data Index: 7745467 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.8673. Min Range: -13.8673
Max Act: 13.4923. Min Act: -0.1700
Data Index: 4832055 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.8673. Min Range: -13.8673
Max Act: 13.4923. Min Act: -0.1700
Data Index: 3416477 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.8673. Min Range: -13.8673
Max Act: 13.4298. Min Act: -0.1700
Data Index: 8422481 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.8673. Min Range: -13.8673
Max Act: 13.3048. Min Act: -0.1700
Data Index: 1632436 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.8673. Min Range: -13.8673
Max Act: 13.4298. Min Act: -0.1700
Data Index: 4187324 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.8673. Min Range: -13.8673
Max Act: 13.3673. Min Act: -0.1700
Data Index: 4470318 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.8673. Min Range: -13.8673
Max Act: 13.3048. Min Act: -0.1700
Data Index: 4568152 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.8673. Min Range: -13.8673
Max Act: 13.3048. Min Act: -0.1700
Data Index: 5316723 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.8673. Min Range: -13.8673
Max Act: 13.2423. Min Act: -0.1700
Data Index: 1991882 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.8673. Min Range: -13.8673
Max Act: 13.1798. Min Act: -0.1700
Data Index: 222772 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.8673. Min Range: -13.8673
Max Act: 13.1173. Min Act: -0.1700
Data Index: 3286671 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.8673. Min Range: -13.8673
Max Act: 13.1173. Min Act: -0.1700
Data Index: 3240176 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.8673. Min Range: -13.8673
Max Act: 13.1173. Min Act: -0.1700
Data Index: 6445464 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.8673. Min Range: -13.8673
Max Act: 13.1173. Min Act: -0.1700
Data Index: 8823174 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.8673. Min Range: -13.8673
Max Act: 13.0548. Min Act: -0.1700
Data Index: 5317758 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.8673. Min Range: -13.8673
Max Act: 13.0548. Min Act: -0.1700
Data Index: 440709 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.8673. Min Range: -13.8673
Max Act: 13.0548. Min Act: -0.1700
Data Index: 3795178 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.8673. Min Range: -13.8673
Max Act: 12.9923. Min Act: -0.1700
Data Index: 7385823 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #19