Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2787 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7227. Min Range: -7.7227
Max Act: 7.7227. Min Act: -0.1700
Data Index: 2518913 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7227. Min Range: -7.7227
Max Act: 7.4727. Min Act: -0.1700
Data Index: 8204741 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7227. Min Range: -7.7227
Max Act: 7.4102. Min Act: -0.1700
Data Index: 4176266 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7227. Min Range: -7.7227
Max Act: 7.3789. Min Act: -0.1700
Data Index: 6275974 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7227. Min Range: -7.7227
Max Act: 7.3789. Min Act: -0.1700
Data Index: 5053202 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7227. Min Range: -7.7227
Max Act: 7.3789. Min Act: -0.1700
Data Index: 221455 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7227. Min Range: -7.7227
Max Act: 7.3477. Min Act: -0.1700
Data Index: 6246522 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7227. Min Range: -7.7227
Max Act: 7.3477. Min Act: -0.1700
Data Index: 6633530 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7227. Min Range: -7.7227
Max Act: 7.3164. Min Act: -0.1700
Data Index: 2377502 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7227. Min Range: -7.7227
Max Act: 7.3164. Min Act: -0.1700
Data Index: 3189407 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7227. Min Range: -7.7227
Max Act: 7.2852. Min Act: -0.1700
Data Index: 876605 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7227. Min Range: -7.7227
Max Act: 7.2852. Min Act: -0.1700
Data Index: 7429104 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7227. Min Range: -7.7227
Max Act: 7.2852. Min Act: -0.1700
Data Index: 725963 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7227. Min Range: -7.7227
Max Act: 7.1914. Min Act: -0.1700
Data Index: 4811711 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7227. Min Range: -7.7227
Max Act: 7.1914. Min Act: -0.1700
Data Index: 5276860 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7227. Min Range: -7.7227
Max Act: 7.2227. Min Act: -0.1700
Data Index: 4516361 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7227. Min Range: -7.7227
Max Act: 7.1914. Min Act: -0.1700
Data Index: 229599 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7227. Min Range: -7.7227
Max Act: 7.1602. Min Act: -0.1700
Data Index: 2138687 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7227. Min Range: -7.7227
Max Act: 7.1289. Min Act: -0.1700
Data Index: 6871266 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7227. Min Range: -7.7227
Max Act: 7.1289. Min Act: -0.1700
Data Index: 8753725 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19