Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 652 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8367. Min Range: -8.8367
Max Act: 8.8367. Min Act: -0.1700
Data Index: 2832312 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8367. Min Range: -8.8367
Max Act: 8.3367. Min Act: -0.1700
Data Index: 942609 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8367. Min Range: -8.8367
Max Act: 8.0867. Min Act: -0.1700
Data Index: 5649286 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8367. Min Range: -8.8367
Max Act: 8.0867. Min Act: -0.1700
Data Index: 2746641 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8367. Min Range: -8.8367
Max Act: 8.0867. Min Act: -0.1700
Data Index: 1369310 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8367. Min Range: -8.8367
Max Act: 8.0867. Min Act: -0.1700
Data Index: 8764870 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8367. Min Range: -8.8367
Max Act: 8.0242. Min Act: -0.1700
Data Index: 2907899 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8367. Min Range: -8.8367
Max Act: 7.9617. Min Act: -0.1700
Data Index: 4024410 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8367. Min Range: -8.8367
Max Act: 7.9617. Min Act: -0.1700
Data Index: 974399 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8367. Min Range: -8.8367
Max Act: 7.9617. Min Act: -0.1700
Data Index: 430301 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8367. Min Range: -8.8367
Max Act: 7.8992. Min Act: -0.1700
Data Index: 6820390 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8367. Min Range: -8.8367
Max Act: 7.8992. Min Act: -0.1700
Data Index: 7009436 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8367. Min Range: -8.8367
Max Act: 7.8367. Min Act: -0.1700
Data Index: 6530220 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8367. Min Range: -8.8367
Max Act: 7.8367. Min Act: -0.1700
Data Index: 7242544 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8367. Min Range: -8.8367
Max Act: 7.8367. Min Act: -0.1700
Data Index: 3009575 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8367. Min Range: -8.8367
Max Act: 7.8367. Min Act: -0.1700
Data Index: 6923820 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8367. Min Range: -8.8367
Max Act: 7.7742. Min Act: -0.1700
Data Index: 8481363 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8367. Min Range: -8.8367
Max Act: 7.7742. Min Act: -0.1700
Data Index: 2657077 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8367. Min Range: -8.8367
Max Act: 7.7742. Min Act: -0.1700
Data Index: 5786936 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8367. Min Range: -8.8367
Max Act: 7.7742. Min Act: -0.1700
Data Index: 6991613 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19