Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6047 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0309. Min Range: -10.0309
Max Act: 10.0309. Min Act: -0.1700
Data Index: 1621440 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0309. Min Range: -10.0309
Max Act: 9.9684. Min Act: -0.1700
Data Index: 6202712 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0309. Min Range: -10.0309
Max Act: 9.9059. Min Act: -0.1698
Data Index: 2216467 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0309. Min Range: -10.0309
Max Act: 9.9059. Min Act: -0.1699
Data Index: 4085400 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0309. Min Range: -10.0309
Max Act: 9.7809. Min Act: -0.1700
Data Index: 8510755 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0309. Min Range: -10.0309
Max Act: 9.7184. Min Act: -0.1700
Data Index: 7609407 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0309. Min Range: -10.0309
Max Act: 9.7184. Min Act: -0.1700
Data Index: 1911367 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0309. Min Range: -10.0309
Max Act: 9.7184. Min Act: -0.1700
Data Index: 1033159 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0309. Min Range: -10.0309
Max Act: 9.7184. Min Act: -0.1700
Data Index: 777688 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0309. Min Range: -10.0309
Max Act: 9.6559. Min Act: -0.1700
Data Index: 2056669 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0309. Min Range: -10.0309
Max Act: 9.5934. Min Act: -0.1700
Data Index: 2863344 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0309. Min Range: -10.0309
Max Act: 9.5934. Min Act: -0.1700
Data Index: 4747466 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0309. Min Range: -10.0309
Max Act: 9.5934. Min Act: -0.1700
Data Index: 3155762 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0309. Min Range: -10.0309
Max Act: 9.5309. Min Act: -0.1700
Data Index: 8202449 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0309. Min Range: -10.0309
Max Act: 9.5309. Min Act: -0.1700
Data Index: 4967302 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0309. Min Range: -10.0309
Max Act: 9.5309. Min Act: -0.1700
Data Index: 4486050 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0309. Min Range: -10.0309
Max Act: 9.5309. Min Act: -0.1700
Data Index: 7367525 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0309. Min Range: -10.0309
Max Act: 9.5934. Min Act: -0.1700
Data Index: 6620977 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0309. Min Range: -10.0309
Max Act: 9.5309. Min Act: -0.1700
Data Index: 3448154 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0309. Min Range: -10.0309
Max Act: 9.5309. Min Act: -0.1694
Data Index: 4694778 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19