Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2989 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8934. Min Range: -4.8934
Max Act: 4.8934. Min Act: -0.1700
Data Index: 7390861 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8934. Min Range: -4.8934
Max Act: 4.7059. Min Act: -0.1700
Data Index: 6590017 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8934. Min Range: -4.8934
Max Act: 4.6434. Min Act: -0.1700
Data Index: 5150608 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8934. Min Range: -4.8934
Max Act: 4.5809. Min Act: -0.1700
Data Index: 5428631 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8934. Min Range: -4.8934
Max Act: 4.5496. Min Act: -0.1700
Data Index: 2156074 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8934. Min Range: -4.8934
Max Act: 4.5496. Min Act: -0.1700
Data Index: 3913211 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8934. Min Range: -4.8934
Max Act: 4.5184. Min Act: -0.1700
Data Index: 8586593 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8934. Min Range: -4.8934
Max Act: 4.5184. Min Act: -0.1700
Data Index: 267904 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8934. Min Range: -4.8934
Max Act: 4.4871. Min Act: -0.1700
Data Index: 5701062 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8934. Min Range: -4.8934
Max Act: 4.4871. Min Act: -0.1700
Data Index: 1244497 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8934. Min Range: -4.8934
Max Act: 4.4559. Min Act: -0.1700
Data Index: 7242941 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8934. Min Range: -4.8934
Max Act: 4.4559. Min Act: -0.1700
Data Index: 6207001 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8934. Min Range: -4.8934
Max Act: 4.4246. Min Act: -0.1700
Data Index: 7029051 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8934. Min Range: -4.8934
Max Act: 4.4246. Min Act: -0.1700
Data Index: 81826 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8934. Min Range: -4.8934
Max Act: 4.3934. Min Act: -0.1700
Data Index: 4591062 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8934. Min Range: -4.8934
Max Act: 4.4246. Min Act: -0.1700
Data Index: 1660443 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8934. Min Range: -4.8934
Max Act: 4.2996. Min Act: -0.1700
Data Index: 1787454 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8934. Min Range: -4.8934
Max Act: 4.3309. Min Act: -0.1700
Data Index: 7425636 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8934. Min Range: -4.8934
Max Act: 4.3621. Min Act: -0.1700
Data Index: 3543987 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8934. Min Range: -4.8934
Max Act: 4.2996. Min Act: -0.1700
Data Index: 2670482 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19