Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3024 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2936. Min Range: -10.2936
Max Act: 10.2936. Min Act: -0.1700
Data Index: 4584034 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2936. Min Range: -10.2936
Max Act: 9.6061. Min Act: -0.1700
Data Index: 6919892 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2936. Min Range: -10.2936
Max Act: 9.5436. Min Act: -0.1700
Data Index: 1542546 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2936. Min Range: -10.2936
Max Act: 9.5436. Min Act: -0.1700
Data Index: 8176156 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2936. Min Range: -10.2936
Max Act: 9.4811. Min Act: -0.1700
Data Index: 4021130 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2936. Min Range: -10.2936
Max Act: 9.4811. Min Act: -0.1700
Data Index: 7342595 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2936. Min Range: -10.2936
Max Act: 9.4811. Min Act: -0.1700
Data Index: 4208455 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2936. Min Range: -10.2936
Max Act: 9.3561. Min Act: -0.1700
Data Index: 3312949 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2936. Min Range: -10.2936
Max Act: 9.3561. Min Act: -0.1700
Data Index: 4590952 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2936. Min Range: -10.2936
Max Act: 9.3561. Min Act: -0.1700
Data Index: 1492387 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2936. Min Range: -10.2936
Max Act: 9.2936. Min Act: -0.1700
Data Index: 1356424 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2936. Min Range: -10.2936
Max Act: 9.2936. Min Act: -0.1700
Data Index: 5694643 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2936. Min Range: -10.2936
Max Act: 9.2936. Min Act: -0.1700
Data Index: 4584033 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2936. Min Range: -10.2936
Max Act: 9.2936. Min Act: -0.1700
Data Index: 2088378 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2936. Min Range: -10.2936
Max Act: 9.1686. Min Act: -0.1700
Data Index: 6756922 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2936. Min Range: -10.2936
Max Act: 9.1686. Min Act: -0.1700
Data Index: 5033653 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2936. Min Range: -10.2936
Max Act: 9.1686. Min Act: -0.1700
Data Index: 1601304 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2936. Min Range: -10.2936
Max Act: 9.1061. Min Act: -0.1700
Data Index: 3277934 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2936. Min Range: -10.2936
Max Act: 9.1061. Min Act: -0.1700
Data Index: 2490326 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2936. Min Range: -10.2936
Max Act: 9.1061. Min Act: -0.1700
Data Index: 5523610 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19