Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1040 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.7475. Min Act: -0.1700
Data Index: 1384432 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.7162. Min Act: -0.1700
Data Index: 3368962 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.6850. Min Act: -0.1700
Data Index: 832344 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.6850. Min Act: -0.1700
Data Index: 6809863 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.5600. Min Act: -0.1700
Data Index: 8417958 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.5287. Min Act: -0.1700
Data Index: 3451017 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.5287. Min Act: -0.1700
Data Index: 941778 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.5287. Min Act: -0.1700
Data Index: 2230094 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.4975. Min Act: -0.1700
Data Index: 1752247 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.4975. Min Act: -0.1700
Data Index: 1181814 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.4975. Min Act: -0.1700
Data Index: 2453142 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.4975. Min Act: -0.1700
Data Index: 7249873 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.4350. Min Act: -0.1700
Data Index: 7387165 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.4350. Min Act: -0.1700
Data Index: 5458475 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.4037. Min Act: -0.1700
Data Index: 7857188 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.4037. Min Act: -0.1700
Data Index: 6460482 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.4037. Min Act: -0.1700
Data Index: 8320622 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.4037. Min Act: -0.1700
Data Index: 4995556 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.4037. Min Act: -0.1700
Data Index: 263598 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7475. Min Range: -6.7475
Max Act: 6.3412. Min Act: -0.1700
Data Index: 1653831 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19