Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5726 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0542. Min Range: -6.0542
Max Act: 6.0542. Min Act: -0.1700
Data Index: 839108 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0542. Min Range: -6.0542
Max Act: 5.9292. Min Act: -0.1700
Data Index: 3393423 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0542. Min Range: -6.0542
Max Act: 5.8667. Min Act: -0.1700
Data Index: 5361286 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0542. Min Range: -6.0542
Max Act: 5.8042. Min Act: -0.1700
Data Index: 5962344 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0542. Min Range: -6.0542
Max Act: 5.7417. Min Act: -0.1700
Data Index: 5365102 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0542. Min Range: -6.0542
Max Act: 5.7104. Min Act: -0.1700
Data Index: 6714520 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0542. Min Range: -6.0542
Max Act: 5.6167. Min Act: -0.1700
Data Index: 5511690 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0542. Min Range: -6.0542
Max Act: 5.5854. Min Act: -0.1699
Data Index: 1673287 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0542. Min Range: -6.0542
Max Act: 5.5854. Min Act: -0.1700
Data Index: 347768 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0542. Min Range: -6.0542
Max Act: 5.5854. Min Act: -0.1700
Data Index: 199185 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0542. Min Range: -6.0542
Max Act: 5.5542. Min Act: -0.1700
Data Index: 1204628 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0542. Min Range: -6.0542
Max Act: 5.4917. Min Act: -0.1700
Data Index: 6428742 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0542. Min Range: -6.0542
Max Act: 5.4604. Min Act: -0.1700
Data Index: 6065025 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0542. Min Range: -6.0542
Max Act: 5.4292. Min Act: -0.1700
Data Index: 6812309 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0542. Min Range: -6.0542
Max Act: 5.4292. Min Act: -0.1700
Data Index: 7601567 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0542. Min Range: -6.0542
Max Act: 5.4292. Min Act: -0.1700
Data Index: 2562099 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0542. Min Range: -6.0542
Max Act: 5.3979. Min Act: -0.1700
Data Index: 7256763 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0542. Min Range: -6.0542
Max Act: 5.3979. Min Act: -0.1700
Data Index: 2440991 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0542. Min Range: -6.0542
Max Act: 5.3667. Min Act: -0.1700
Data Index: 909131 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0542. Min Range: -6.0542
Max Act: 5.3354. Min Act: -0.1700
Data Index: 2815149 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19