Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 512 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5039. Min Range: -4.5039
Max Act: 4.4727. Min Act: -0.1700
Data Index: 5036372 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5039. Min Range: -4.5039
Max Act: 4.5039. Min Act: -0.1700
Data Index: 2807974 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5039. Min Range: -4.5039
Max Act: 4.4102. Min Act: -0.1700
Data Index: 1353996 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5039. Min Range: -4.5039
Max Act: 4.3789. Min Act: -0.1700
Data Index: 8250625 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5039. Min Range: -4.5039
Max Act: 4.3164. Min Act: -0.1700
Data Index: 6624000 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5039. Min Range: -4.5039
Max Act: 4.2852. Min Act: -0.1700
Data Index: 398948 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5039. Min Range: -4.5039
Max Act: 4.3164. Min Act: -0.1700
Data Index: 8830328 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5039. Min Range: -4.5039
Max Act: 4.2227. Min Act: -0.1700
Data Index: 1877834 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5039. Min Range: -4.5039
Max Act: 4.2227. Min Act: -0.1700
Data Index: 753566 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5039. Min Range: -4.5039
Max Act: 4.2539. Min Act: -0.1700
Data Index: 1711830 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5039. Min Range: -4.5039
Max Act: 4.2539. Min Act: -0.1700
Data Index: 3826985 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5039. Min Range: -4.5039
Max Act: 4.2539. Min Act: -0.1700
Data Index: 6619951 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5039. Min Range: -4.5039
Max Act: 4.1289. Min Act: -0.1700
Data Index: 4077517 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5039. Min Range: -4.5039
Max Act: 4.2227. Min Act: -0.1700
Data Index: 7294436 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5039. Min Range: -4.5039
Max Act: 4.2227. Min Act: -0.1700
Data Index: 8126960 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5039. Min Range: -4.5039
Max Act: 4.1914. Min Act: -0.1700
Data Index: 229247 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5039. Min Range: -4.5039
Max Act: 4.2227. Min Act: -0.1700
Data Index: 8340287 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5039. Min Range: -4.5039
Max Act: 4.1602. Min Act: -0.1700
Data Index: 3491371 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5039. Min Range: -4.5039
Max Act: 4.1914. Min Act: -0.1700
Data Index: 4750605 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5039. Min Range: -4.5039
Max Act: 4.2227. Min Act: -0.1700
Data Index: 8445062 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19