Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6189 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3456. Min Range: -8.3456
Max Act: 8.3456. Min Act: -0.1700
Data Index: 1903888 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3456. Min Range: -8.3456
Max Act: 8.2206. Min Act: -0.1700
Data Index: 4892079 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3456. Min Range: -8.3456
Max Act: 8.0331. Min Act: -0.1700
Data Index: 229549 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3456. Min Range: -8.3456
Max Act: 7.8456. Min Act: -0.1700
Data Index: 1878836 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3456. Min Range: -8.3456
Max Act: 7.8143. Min Act: -0.1700
Data Index: 5838532 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3456. Min Range: -8.3456
Max Act: 7.7518. Min Act: -0.1700
Data Index: 3658559 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3456. Min Range: -8.3456
Max Act: 7.7518. Min Act: -0.1700
Data Index: 2277746 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3456. Min Range: -8.3456
Max Act: 7.6893. Min Act: -0.1700
Data Index: 8829497 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3456. Min Range: -8.3456
Max Act: 7.6581. Min Act: -0.1700
Data Index: 4469697 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3456. Min Range: -8.3456
Max Act: 7.5956. Min Act: -0.1700
Data Index: 6842479 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3456. Min Range: -8.3456
Max Act: 7.5643. Min Act: -0.1700
Data Index: 3963463 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3456. Min Range: -8.3456
Max Act: 7.5956. Min Act: -0.1700
Data Index: 111228 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3456. Min Range: -8.3456
Max Act: 7.5643. Min Act: -0.1700
Data Index: 5098442 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3456. Min Range: -8.3456
Max Act: 7.5643. Min Act: -0.1700
Data Index: 3854916 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3456. Min Range: -8.3456
Max Act: 7.5643. Min Act: -0.1700
Data Index: 6902381 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3456. Min Range: -8.3456
Max Act: 7.5331. Min Act: -0.1700
Data Index: 2670977 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3456. Min Range: -8.3456
Max Act: 7.4393. Min Act: -0.1700
Data Index: 8300468 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3456. Min Range: -8.3456
Max Act: 7.4706. Min Act: -0.1700
Data Index: 917378 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3456. Min Range: -8.3456
Max Act: 7.4706. Min Act: -0.1700
Data Index: 5564370 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3456. Min Range: -8.3456
Max Act: 7.4706. Min Act: -0.1700
Data Index: 3100286 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19