Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4717 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8963. Min Range: -8.8963
Max Act: 8.8963. Min Act: -0.1700
Data Index: 1937199 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8963. Min Range: -8.8963
Max Act: 8.5838. Min Act: -0.1700
Data Index: 5609557 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8963. Min Range: -8.8963
Max Act: 8.5213. Min Act: -0.1700
Data Index: 7963767 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8963. Min Range: -8.8963
Max Act: 8.5213. Min Act: -0.1700
Data Index: 4757456 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8963. Min Range: -8.8963
Max Act: 8.4588. Min Act: -0.1700
Data Index: 5552641 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8963. Min Range: -8.8963
Max Act: 8.4588. Min Act: -0.1700
Data Index: 8030485 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8963. Min Range: -8.8963
Max Act: 8.3963. Min Act: -0.1700
Data Index: 6363568 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8963. Min Range: -8.8963
Max Act: 8.3963. Min Act: -0.1700
Data Index: 8649396 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8963. Min Range: -8.8963
Max Act: 8.3963. Min Act: -0.1700
Data Index: 4781068 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8963. Min Range: -8.8963
Max Act: 8.3963. Min Act: -0.1700
Data Index: 8614047 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8963. Min Range: -8.8963
Max Act: 8.3338. Min Act: -0.1700
Data Index: 8671605 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8963. Min Range: -8.8963
Max Act: 8.3338. Min Act: -0.1700
Data Index: 2326786 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8963. Min Range: -8.8963
Max Act: 8.3338. Min Act: -0.1700
Data Index: 7092331 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8963. Min Range: -8.8963
Max Act: 8.3338. Min Act: -0.1700
Data Index: 1628501 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8963. Min Range: -8.8963
Max Act: 8.3338. Min Act: -0.1700
Data Index: 1633640 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8963. Min Range: -8.8963
Max Act: 8.3338. Min Act: -0.1700
Data Index: 7541013 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8963. Min Range: -8.8963
Max Act: 8.3338. Min Act: -0.1700
Data Index: 8647826 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8963. Min Range: -8.8963
Max Act: 8.2713. Min Act: -0.1700
Data Index: 4038117 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8963. Min Range: -8.8963
Max Act: 8.2713. Min Act: -0.1700
Data Index: 4226883 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8963. Min Range: -8.8963
Max Act: 8.2713. Min Act: -0.1700
Data Index: 2912551 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19