Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1540 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7591. Min Range: -6.7591
Max Act: 6.7591. Min Act: -0.1700
Data Index: 6168884 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7591. Min Range: -6.7591
Max Act: 6.5403. Min Act: -0.1700
Data Index: 414862 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7591. Min Range: -6.7591
Max Act: 6.4466. Min Act: -0.1700
Data Index: 2817666 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7591. Min Range: -6.7591
Max Act: 6.4153. Min Act: -0.1700
Data Index: 290008 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7591. Min Range: -6.7591
Max Act: 6.4153. Min Act: -0.1700
Data Index: 54937 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7591. Min Range: -6.7591
Max Act: 6.3841. Min Act: -0.1700
Data Index: 2728296 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7591. Min Range: -6.7591
Max Act: 6.3216. Min Act: -0.1700
Data Index: 1026447 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7591. Min Range: -6.7591
Max Act: 6.3216. Min Act: -0.1700
Data Index: 6354769 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7591. Min Range: -6.7591
Max Act: 6.3216. Min Act: -0.1700
Data Index: 1726348 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7591. Min Range: -6.7591
Max Act: 6.2903. Min Act: -0.1700
Data Index: 3761762 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7591. Min Range: -6.7591
Max Act: 6.3216. Min Act: -0.1700
Data Index: 8806001 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7591. Min Range: -6.7591
Max Act: 6.2903. Min Act: -0.1700
Data Index: 7266865 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7591. Min Range: -6.7591
Max Act: 6.2591. Min Act: -0.1700
Data Index: 5273740 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7591. Min Range: -6.7591
Max Act: 6.2278. Min Act: -0.1700
Data Index: 4604986 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7591. Min Range: -6.7591
Max Act: 6.2591. Min Act: -0.1700
Data Index: 3128250 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7591. Min Range: -6.7591
Max Act: 6.2278. Min Act: -0.1700
Data Index: 1097247 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7591. Min Range: -6.7591
Max Act: 6.1966. Min Act: -0.1700
Data Index: 2691537 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7591. Min Range: -6.7591
Max Act: 6.1653. Min Act: -0.1700
Data Index: 799768 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7591. Min Range: -6.7591
Max Act: 6.1653. Min Act: -0.1700
Data Index: 6441534 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7591. Min Range: -6.7591
Max Act: 6.1653. Min Act: -0.1700
Data Index: 3776714 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19