Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3169 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1825. Min Range: -3.1825
Max Act: 3.1825. Min Act: -0.1700
Data Index: 5069870 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1825. Min Range: -3.1825
Max Act: 3.1353. Min Act: -0.1700
Data Index: 5822133 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1825. Min Range: -3.1825
Max Act: 3.0249. Min Act: -0.1700
Data Index: 7988797 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1825. Min Range: -3.1825
Max Act: 3.0407. Min Act: -0.1700
Data Index: 6589142 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1825. Min Range: -3.1825
Max Act: 3.0091. Min Act: -0.1700
Data Index: 2079319 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1825. Min Range: -3.1825
Max Act: 3.0091. Min Act: -0.1700
Data Index: 7161496 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1825. Min Range: -3.1825
Max Act: 3.0091. Min Act: -0.1700
Data Index: 6905729 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1825. Min Range: -3.1825
Max Act: 3.0091. Min Act: -0.1700
Data Index: 5180760 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1825. Min Range: -3.1825
Max Act: 2.9933. Min Act: -0.1700
Data Index: 1819581 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1825. Min Range: -3.1825
Max Act: 2.9933. Min Act: -0.1700
Data Index: 148647 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1825. Min Range: -3.1825
Max Act: 2.9617. Min Act: -0.1700
Data Index: 6438281 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1825. Min Range: -3.1825
Max Act: 2.9775. Min Act: -0.1700
Data Index: 803377 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1825. Min Range: -3.1825
Max Act: 2.9775. Min Act: -0.1700
Data Index: 6165555 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1825. Min Range: -3.1825
Max Act: 2.9459. Min Act: -0.1700
Data Index: 4224914 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1825. Min Range: -3.1825
Max Act: 2.9617. Min Act: -0.1700
Data Index: 600709 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1825. Min Range: -3.1825
Max Act: 2.9459. Min Act: -0.1700
Data Index: 3266095 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1825. Min Range: -3.1825
Max Act: 2.9459. Min Act: -0.1700
Data Index: 276437 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1825. Min Range: -3.1825
Max Act: 2.9300. Min Act: -0.1700
Data Index: 5945250 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1825. Min Range: -3.1825
Max Act: 2.9459. Min Act: -0.1700
Data Index: 7504540 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1825. Min Range: -3.1825
Max Act: 2.9459. Min Act: -0.1700
Data Index: 7687894 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19