Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1534 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6953. Min Range: -6.6953
Max Act: 6.6953. Min Act: -0.1700
Data Index: 6121054 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6953. Min Range: -6.6953
Max Act: 6.4765. Min Act: -0.1700
Data Index: 663598 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6953. Min Range: -6.6953
Max Act: 6.3203. Min Act: -0.1700
Data Index: 7176592 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6953. Min Range: -6.6953
Max Act: 6.2890. Min Act: -0.1700
Data Index: 1659020 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6953. Min Range: -6.6953
Max Act: 6.2890. Min Act: -0.1700
Data Index: 599711 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6953. Min Range: -6.6953
Max Act: 6.3203. Min Act: -0.1700
Data Index: 3348966 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6953. Min Range: -6.6953
Max Act: 6.2265. Min Act: -0.1700
Data Index: 371070 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6953. Min Range: -6.6953
Max Act: 6.2265. Min Act: -0.1700
Data Index: 4400080 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6953. Min Range: -6.6953
Max Act: 6.2265. Min Act: -0.1700
Data Index: 4703132 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6953. Min Range: -6.6953
Max Act: 6.1640. Min Act: -0.1700
Data Index: 2202909 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6953. Min Range: -6.6953
Max Act: 6.1328. Min Act: -0.1700
Data Index: 6427052 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6953. Min Range: -6.6953
Max Act: 6.1015. Min Act: -0.1700
Data Index: 6288503 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6953. Min Range: -6.6953
Max Act: 6.1015. Min Act: -0.1700
Data Index: 8805488 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6953. Min Range: -6.6953
Max Act: 6.0703. Min Act: -0.1700
Data Index: 4965119 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6953. Min Range: -6.6953
Max Act: 6.0390. Min Act: -0.1700
Data Index: 2833123 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6953. Min Range: -6.6953
Max Act: 6.0078. Min Act: -0.1700
Data Index: 7254751 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6953. Min Range: -6.6953
Max Act: 6.0390. Min Act: -0.1700
Data Index: 5717272 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6953. Min Range: -6.6953
Max Act: 6.0390. Min Act: -0.1700
Data Index: 1005573 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6953. Min Range: -6.6953
Max Act: 6.0078. Min Act: -0.1700
Data Index: 3815829 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6953. Min Range: -6.6953
Max Act: 6.0078. Min Act: -0.1700
Data Index: 3410565 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19