Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2641 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9375. Min Range: -7.9375
Max Act: 7.9375. Min Act: -0.1700
Data Index: 2725518 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9375. Min Range: -7.9375
Max Act: 7.9375. Min Act: -0.1700
Data Index: 7083979 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9375. Min Range: -7.9375
Max Act: 7.8750. Min Act: -0.1700
Data Index: 7781243 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9375. Min Range: -7.9375
Max Act: 7.8125. Min Act: -0.1700
Data Index: 8537409 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9375. Min Range: -7.9375
Max Act: 7.8125. Min Act: -0.1700
Data Index: 1786846 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9375. Min Range: -7.9375
Max Act: 7.8125. Min Act: -0.1700
Data Index: 4752461 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9375. Min Range: -7.9375
Max Act: 7.7500. Min Act: -0.1700
Data Index: 1980501 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9375. Min Range: -7.9375
Max Act: 7.7188. Min Act: -0.1700
Data Index: 6325463 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9375. Min Range: -7.9375
Max Act: 7.7188. Min Act: -0.1700
Data Index: 2754390 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9375. Min Range: -7.9375
Max Act: 7.6875. Min Act: -0.1700
Data Index: 8820999 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9375. Min Range: -7.9375
Max Act: 7.6563. Min Act: -0.1700
Data Index: 8779871 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9375. Min Range: -7.9375
Max Act: 7.6563. Min Act: -0.1700
Data Index: 3458438 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9375. Min Range: -7.9375
Max Act: 7.5938. Min Act: -0.1700
Data Index: 540700 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9375. Min Range: -7.9375
Max Act: 7.6250. Min Act: -0.1700
Data Index: 6160346 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9375. Min Range: -7.9375
Max Act: 7.6250. Min Act: -0.1700
Data Index: 5110411 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9375. Min Range: -7.9375
Max Act: 7.6250. Min Act: -0.1700
Data Index: 642902 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9375. Min Range: -7.9375
Max Act: 7.6250. Min Act: -0.1700
Data Index: 2823299 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9375. Min Range: -7.9375
Max Act: 7.5625. Min Act: -0.1700
Data Index: 3058636 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9375. Min Range: -7.9375
Max Act: 7.5625. Min Act: -0.1700
Data Index: 1381403 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9375. Min Range: -7.9375
Max Act: 7.5938. Min Act: -0.1700
Data Index: 3549303 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19