Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 498 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6260. Min Range: -6.6260
Max Act: 6.6260. Min Act: -0.1700
Data Index: 3701323 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6260. Min Range: -6.6260
Max Act: 6.5010. Min Act: -0.1700
Data Index: 3905136 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6260. Min Range: -6.6260
Max Act: 6.4698. Min Act: -0.1700
Data Index: 3132677 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6260. Min Range: -6.6260
Max Act: 6.4698. Min Act: -0.1700
Data Index: 211768 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6260. Min Range: -6.6260
Max Act: 6.4698. Min Act: -0.1700
Data Index: 7680054 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6260. Min Range: -6.6260
Max Act: 6.4385. Min Act: -0.1700
Data Index: 5530526 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6260. Min Range: -6.6260
Max Act: 6.3760. Min Act: -0.1700
Data Index: 1440133 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6260. Min Range: -6.6260
Max Act: 6.3760. Min Act: -0.1700
Data Index: 2116371 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6260. Min Range: -6.6260
Max Act: 6.3135. Min Act: -0.1700
Data Index: 6667654 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6260. Min Range: -6.6260
Max Act: 6.3760. Min Act: -0.1700
Data Index: 30917 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6260. Min Range: -6.6260
Max Act: 6.3135. Min Act: -0.1700
Data Index: 5742985 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6260. Min Range: -6.6260
Max Act: 6.2823. Min Act: -0.1700
Data Index: 4937870 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6260. Min Range: -6.6260
Max Act: 6.2510. Min Act: -0.1700
Data Index: 7292079 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6260. Min Range: -6.6260
Max Act: 6.2823. Min Act: -0.1700
Data Index: 1455819 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6260. Min Range: -6.6260
Max Act: 6.2510. Min Act: -0.1700
Data Index: 917817 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6260. Min Range: -6.6260
Max Act: 6.2510. Min Act: -0.1700
Data Index: 6969987 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6260. Min Range: -6.6260
Max Act: 6.2510. Min Act: -0.1700
Data Index: 1663236 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6260. Min Range: -6.6260
Max Act: 6.2510. Min Act: -0.1700
Data Index: 7530835 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6260. Min Range: -6.6260
Max Act: 6.2198. Min Act: -0.1700
Data Index: 19898 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6260. Min Range: -6.6260
Max Act: 6.2198. Min Act: -0.1700
Data Index: 2650898 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19