Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3680 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.4977. Min Act: -0.1700
Data Index: 6694879 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.1851. Min Act: -0.1700
Data Index: 2134962 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.1851. Min Act: -0.1700
Data Index: 2373922 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.1539. Min Act: -0.1700
Data Index: 3838695 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.1226. Min Act: -0.1700
Data Index: 6069638 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.1226. Min Act: -0.1700
Data Index: 6069640 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.1226. Min Act: -0.1700
Data Index: 835856 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.0914. Min Act: -0.1700
Data Index: 821917 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.0914. Min Act: -0.1700
Data Index: 821920 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.0601. Min Act: -0.1700
Data Index: 1937966 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.0601. Min Act: -0.1700
Data Index: 6069642 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.0601. Min Act: -0.1700
Data Index: 835858 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.0601. Min Act: -0.1700
Data Index: 2373924 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.0289. Min Act: -0.1700
Data Index: 3838697 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.0601. Min Act: -0.1700
Data Index: 6008873 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.0601. Min Act: -0.1700
Data Index: 8388187 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4977. Min Range: -4.4977
Max Act: 3.9976. Min Act: -0.1700
Data Index: 8174414 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4977. Min Range: -4.4977
Max Act: 3.9976. Min Act: -0.1700
Data Index: 7844174 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.0289. Min Act: -0.1700
Data Index: 2134965 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4977. Min Range: -4.4977
Max Act: 4.0289. Min Act: -0.1700
Data Index: 5856006 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19