Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3572 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4064. Min Range: -4.4064
Max Act: 4.4064. Min Act: -0.1700
Data Index: 5407251 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4064. Min Range: -4.4064
Max Act: 4.2814. Min Act: -0.1700
Data Index: 2138296 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4064. Min Range: -4.4064
Max Act: 4.2501. Min Act: -0.1700
Data Index: 2816705 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4064. Min Range: -4.4064
Max Act: 4.2501. Min Act: -0.1700
Data Index: 7288382 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4064. Min Range: -4.4064
Max Act: 4.1876. Min Act: -0.1700
Data Index: 4667451 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4064. Min Range: -4.4064
Max Act: 4.1876. Min Act: -0.1700
Data Index: 6736853 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4064. Min Range: -4.4064
Max Act: 4.1563. Min Act: -0.1700
Data Index: 674593 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4064. Min Range: -4.4064
Max Act: 4.1563. Min Act: -0.1700
Data Index: 1643879 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4064. Min Range: -4.4064
Max Act: 4.1563. Min Act: -0.1700
Data Index: 3761622 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4064. Min Range: -4.4064
Max Act: 4.1251. Min Act: -0.1700
Data Index: 6440134 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4064. Min Range: -4.4064
Max Act: 4.1251. Min Act: -0.1700
Data Index: 2248400 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4064. Min Range: -4.4064
Max Act: 4.1251. Min Act: -0.1700
Data Index: 6498123 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4064. Min Range: -4.4064
Max Act: 4.1251. Min Act: -0.1700
Data Index: 2414240 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4064. Min Range: -4.4064
Max Act: 4.0938. Min Act: -0.1700
Data Index: 5401216 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4064. Min Range: -4.4064
Max Act: 4.0626. Min Act: -0.1700
Data Index: 6991635 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4064. Min Range: -4.4064
Max Act: 4.0626. Min Act: -0.1700
Data Index: 6423323 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4064. Min Range: -4.4064
Max Act: 4.0626. Min Act: -0.1700
Data Index: 421939 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4064. Min Range: -4.4064
Max Act: 4.0626. Min Act: -0.1700
Data Index: 232035 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4064. Min Range: -4.4064
Max Act: 4.0313. Min Act: -0.1700
Data Index: 4106091 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4064. Min Range: -4.4064
Max Act: 4.0313. Min Act: -0.1700
Data Index: 4603613 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19