Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1045 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3975. Min Range: -5.3975
Max Act: 5.3975. Min Act: -0.1700
Data Index: 2104160 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3975. Min Range: -5.3975
Max Act: 5.3975. Min Act: -0.1700
Data Index: 1583453 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3975. Min Range: -5.3975
Max Act: 5.3037. Min Act: -0.1700
Data Index: 3540043 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3975. Min Range: -5.3975
Max Act: 5.1787. Min Act: -0.1700
Data Index: 6244122 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3975. Min Range: -5.3975
Max Act: 5.1162. Min Act: -0.1700
Data Index: 1100042 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3975. Min Range: -5.3975
Max Act: 5.1162. Min Act: -0.1700
Data Index: 7570659 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3975. Min Range: -5.3975
Max Act: 5.0850. Min Act: -0.1700
Data Index: 4496114 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3975. Min Range: -5.3975
Max Act: 5.0850. Min Act: -0.1700
Data Index: 8754474 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3975. Min Range: -5.3975
Max Act: 5.0225. Min Act: -0.1700
Data Index: 6244123 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3975. Min Range: -5.3975
Max Act: 5.0225. Min Act: -0.1700
Data Index: 1751741 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3975. Min Range: -5.3975
Max Act: 5.0225. Min Act: -0.1700
Data Index: 6995131 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3975. Min Range: -5.3975
Max Act: 4.9912. Min Act: -0.1700
Data Index: 126711 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3975. Min Range: -5.3975
Max Act: 4.9912. Min Act: -0.1700
Data Index: 6244121 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3975. Min Range: -5.3975
Max Act: 5.0225. Min Act: -0.1700
Data Index: 1134155 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3975. Min Range: -5.3975
Max Act: 4.9287. Min Act: -0.1700
Data Index: 1240015 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3975. Min Range: -5.3975
Max Act: 4.8975. Min Act: -0.1700
Data Index: 4710130 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3975. Min Range: -5.3975
Max Act: 4.8662. Min Act: -0.1700
Data Index: 1738644 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3975. Min Range: -5.3975
Max Act: 4.8662. Min Act: -0.1700
Data Index: 8060353 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3975. Min Range: -5.3975
Max Act: 4.8350. Min Act: -0.1700
Data Index: 5153915 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3975. Min Range: -5.3975
Max Act: 4.8350. Min Act: -0.1700
Data Index: 6892966 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19