Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5853 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8398. Min Range: -6.8398
Max Act: 6.8085. Min Act: -0.1700
Data Index: 7485390 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8398. Min Range: -6.8398
Max Act: 6.8398. Min Act: -0.1700
Data Index: 6127109 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8398. Min Range: -6.8398
Max Act: 6.7773. Min Act: -0.1700
Data Index: 1203727 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8398. Min Range: -6.8398
Max Act: 6.7148. Min Act: -0.1700
Data Index: 8588991 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8398. Min Range: -6.8398
Max Act: 6.6523. Min Act: -0.1700
Data Index: 4009720 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8398. Min Range: -6.8398
Max Act: 6.6523. Min Act: -0.1700
Data Index: 7784293 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8398. Min Range: -6.8398
Max Act: 6.6523. Min Act: -0.1700
Data Index: 5512467 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8398. Min Range: -6.8398
Max Act: 6.6210. Min Act: -0.1700
Data Index: 3094909 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8398. Min Range: -6.8398
Max Act: 6.5898. Min Act: -0.1700
Data Index: 3266043 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8398. Min Range: -6.8398
Max Act: 6.5585. Min Act: -0.1700
Data Index: 5907566 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8398. Min Range: -6.8398
Max Act: 6.5273. Min Act: -0.1700
Data Index: 4716802 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8398. Min Range: -6.8398
Max Act: 6.4960. Min Act: -0.1700
Data Index: 1542648 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8398. Min Range: -6.8398
Max Act: 6.4960. Min Act: -0.1700
Data Index: 77858 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8398. Min Range: -6.8398
Max Act: 6.4648. Min Act: -0.1700
Data Index: 4057730 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8398. Min Range: -6.8398
Max Act: 6.4648. Min Act: -0.1700
Data Index: 4807287 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8398. Min Range: -6.8398
Max Act: 6.4648. Min Act: -0.1700
Data Index: 8647036 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8398. Min Range: -6.8398
Max Act: 6.4648. Min Act: -0.1700
Data Index: 6223186 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8398. Min Range: -6.8398
Max Act: 6.4648. Min Act: -0.1700
Data Index: 4847903 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8398. Min Range: -6.8398
Max Act: 6.4648. Min Act: -0.1700
Data Index: 4284245 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8398. Min Range: -6.8398
Max Act: 6.4335. Min Act: -0.1700
Data Index: 4566792 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19