Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3493 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5559. Min Range: -6.5559
Max Act: 6.5559. Min Act: -0.1700
Data Index: 3146563 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5559. Min Range: -6.5559
Max Act: 6.4309. Min Act: -0.1700
Data Index: 5555408 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5559. Min Range: -6.5559
Max Act: 6.3997. Min Act: -0.1700
Data Index: 2099936 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5559. Min Range: -6.5559
Max Act: 6.3684. Min Act: -0.1700
Data Index: 2572793 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5559. Min Range: -6.5559
Max Act: 6.3059. Min Act: -0.1700
Data Index: 4477972 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5559. Min Range: -6.5559
Max Act: 6.2747. Min Act: -0.1700
Data Index: 2412466 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5559. Min Range: -6.5559
Max Act: 6.2434. Min Act: -0.1700
Data Index: 5013001 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5559. Min Range: -6.5559
Max Act: 6.2122. Min Act: -0.1700
Data Index: 2584825 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5559. Min Range: -6.5559
Max Act: 6.1809. Min Act: -0.1700
Data Index: 7873173 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5559. Min Range: -6.5559
Max Act: 6.1809. Min Act: -0.1700
Data Index: 5342892 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5559. Min Range: -6.5559
Max Act: 6.1497. Min Act: -0.1700
Data Index: 5585682 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5559. Min Range: -6.5559
Max Act: 6.1497. Min Act: -0.1700
Data Index: 1686140 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5559. Min Range: -6.5559
Max Act: 6.1184. Min Act: -0.1700
Data Index: 6953475 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5559. Min Range: -6.5559
Max Act: 6.1184. Min Act: -0.1700
Data Index: 6332648 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5559. Min Range: -6.5559
Max Act: 6.1184. Min Act: -0.1700
Data Index: 6432101 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5559. Min Range: -6.5559
Max Act: 6.0872. Min Act: -0.1700
Data Index: 4028906 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5559. Min Range: -6.5559
Max Act: 6.1184. Min Act: -0.1700
Data Index: 156971 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5559. Min Range: -6.5559
Max Act: 6.0872. Min Act: -0.1700
Data Index: 1421621 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5559. Min Range: -6.5559
Max Act: 6.0559. Min Act: -0.1700
Data Index: 6002238 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5559. Min Range: -6.5559
Max Act: 6.0559. Min Act: -0.1700
Data Index: 2619969 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19