Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3419 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2057. Min Range: -5.2057
Max Act: 5.1745. Min Act: -0.1700
Data Index: 1996674 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2057. Min Range: -5.2057
Max Act: 5.2057. Min Act: -0.1700
Data Index: 7531989 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2057. Min Range: -5.2057
Max Act: 5.1745. Min Act: -0.1700
Data Index: 6903821 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2057. Min Range: -5.2057
Max Act: 5.0495. Min Act: -0.1700
Data Index: 8415448 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2057. Min Range: -5.2057
Max Act: 4.9870. Min Act: -0.1700
Data Index: 8415442 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2057. Min Range: -5.2057
Max Act: 4.9870. Min Act: -0.1700
Data Index: 7531985 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2057. Min Range: -5.2057
Max Act: 4.9245. Min Act: -0.1700
Data Index: 1996671 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2057. Min Range: -5.2057
Max Act: 4.9245. Min Act: -0.1700
Data Index: 256819 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2057. Min Range: -5.2057
Max Act: 4.9245. Min Act: -0.1700
Data Index: 1996678 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2057. Min Range: -5.2057
Max Act: 4.8932. Min Act: -0.1700
Data Index: 1996664 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2057. Min Range: -5.2057
Max Act: 4.8932. Min Act: -0.1700
Data Index: 71662 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2057. Min Range: -5.2057
Max Act: 4.7682. Min Act: -0.1700
Data Index: 7531990 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2057. Min Range: -5.2057
Max Act: 4.7682. Min Act: -0.1700
Data Index: 7531984 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2057. Min Range: -5.2057
Max Act: 4.7682. Min Act: -0.1700
Data Index: 1996670 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2057. Min Range: -5.2057
Max Act: 4.7682. Min Act: -0.1700
Data Index: 4168146 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2057. Min Range: -5.2057
Max Act: 4.7370. Min Act: -0.1700
Data Index: 7531979 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2057. Min Range: -5.2057
Max Act: 4.7057. Min Act: -0.1700
Data Index: 6903822 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2057. Min Range: -5.2057
Max Act: 4.7370. Min Act: -0.1700
Data Index: 7531981 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2057. Min Range: -5.2057
Max Act: 4.7370. Min Act: -0.1700
Data Index: 71664 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2057. Min Range: -5.2057
Max Act: 4.7057. Min Act: -0.1700
Data Index: 1996667 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19