Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 357 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8959. Min Range: -2.8959
Max Act: 2.8959. Min Act: -0.1700
Data Index: 752626 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8959. Min Range: -2.8959
Max Act: 2.8800. Min Act: -0.1700
Data Index: 2381363 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8959. Min Range: -2.8959
Max Act: 2.8800. Min Act: -0.1700
Data Index: 7957213 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8959. Min Range: -2.8959
Max Act: 2.8641. Min Act: -0.1700
Data Index: 8704035 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8959. Min Range: -2.8959
Max Act: 2.8323. Min Act: -0.1700
Data Index: 4979420 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8959. Min Range: -2.8959
Max Act: 2.8482. Min Act: -0.1700
Data Index: 6754775 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8959. Min Range: -2.8959
Max Act: 2.8482. Min Act: -0.1700
Data Index: 8170805 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8959. Min Range: -2.8959
Max Act: 2.8164. Min Act: -0.1700
Data Index: 7216103 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8959. Min Range: -2.8959
Max Act: 2.8323. Min Act: -0.1700
Data Index: 3283652 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8959. Min Range: -2.8959
Max Act: 2.8164. Min Act: -0.1700
Data Index: 8321992 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8959. Min Range: -2.8959
Max Act: 2.8164. Min Act: -0.1700
Data Index: 5302859 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8959. Min Range: -2.8959
Max Act: 2.8164. Min Act: -0.1700
Data Index: 3256989 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8959. Min Range: -2.8959
Max Act: 2.8164. Min Act: -0.1700
Data Index: 1166136 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8959. Min Range: -2.8959
Max Act: 2.7846. Min Act: -0.1700
Data Index: 7752737 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8959. Min Range: -2.8959
Max Act: 2.8164. Min Act: -0.1700
Data Index: 670343 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8959. Min Range: -2.8959
Max Act: 2.8164. Min Act: -0.1700
Data Index: 2827898 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8959. Min Range: -2.8959
Max Act: 2.7846. Min Act: -0.1700
Data Index: 3086853 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8959. Min Range: -2.8959
Max Act: 2.7846. Min Act: -0.1700
Data Index: 4316918 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8959. Min Range: -2.8959
Max Act: 2.8005. Min Act: -0.1700
Data Index: 5305126 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8959. Min Range: -2.8959
Max Act: 2.8005. Min Act: -0.1700
Data Index: 1443437 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19