Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3473 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1934. Min Range: -5.1934
Max Act: 5.1934. Min Act: -0.1700
Data Index: 8245440 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1934. Min Range: -5.1934
Max Act: 5.0997. Min Act: -0.1700
Data Index: 3261017 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1934. Min Range: -5.1934
Max Act: 5.0684. Min Act: -0.1700
Data Index: 6029833 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1934. Min Range: -5.1934
Max Act: 5.0372. Min Act: -0.1700
Data Index: 1509345 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1934. Min Range: -5.1934
Max Act: 4.9747. Min Act: -0.1700
Data Index: 3755825 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1934. Min Range: -5.1934
Max Act: 4.9122. Min Act: -0.1700
Data Index: 5744450 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1934. Min Range: -5.1934
Max Act: 4.9434. Min Act: -0.1700
Data Index: 7557718 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1934. Min Range: -5.1934
Max Act: 4.9122. Min Act: -0.1700
Data Index: 5495992 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1934. Min Range: -5.1934
Max Act: 4.8809. Min Act: -0.1700
Data Index: 4854496 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1934. Min Range: -5.1934
Max Act: 4.8809. Min Act: -0.1700
Data Index: 1556716 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1934. Min Range: -5.1934
Max Act: 4.9122. Min Act: -0.1700
Data Index: 4418364 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1934. Min Range: -5.1934
Max Act: 4.8497. Min Act: -0.1700
Data Index: 1333490 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1934. Min Range: -5.1934
Max Act: 4.8497. Min Act: -0.1700
Data Index: 1964403 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1934. Min Range: -5.1934
Max Act: 4.8184. Min Act: -0.1700
Data Index: 1243044 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1934. Min Range: -5.1934
Max Act: 4.7872. Min Act: -0.1700
Data Index: 5815862 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1934. Min Range: -5.1934
Max Act: 4.7872. Min Act: -0.1700
Data Index: 5899604 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1934. Min Range: -5.1934
Max Act: 4.8184. Min Act: -0.1700
Data Index: 3131900 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1934. Min Range: -5.1934
Max Act: 4.8184. Min Act: -0.1700
Data Index: 6571376 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1934. Min Range: -5.1934
Max Act: 4.8184. Min Act: -0.1700
Data Index: 5460344 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1934. Min Range: -5.1934
Max Act: 4.7872. Min Act: -0.1700
Data Index: 4789640 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19