Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5501 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5373. Min Range: -3.5373
Max Act: 3.5373. Min Act: -0.1700
Data Index: 7357079 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5373. Min Range: -3.5373
Max Act: 3.5216. Min Act: -0.1700
Data Index: 8316171 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5373. Min Range: -3.5373
Max Act: 3.5216. Min Act: -0.1700
Data Index: 844600 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5373. Min Range: -3.5373
Max Act: 3.5060. Min Act: -0.1700
Data Index: 8108943 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5373. Min Range: -3.5373
Max Act: 3.5060. Min Act: -0.1700
Data Index: 378143 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5373. Min Range: -3.5373
Max Act: 3.5060. Min Act: -0.1700
Data Index: 528605 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5373. Min Range: -3.5373
Max Act: 3.5216. Min Act: -0.1700
Data Index: 4393000 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5373. Min Range: -3.5373
Max Act: 3.4903. Min Act: -0.1700
Data Index: 7582162 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5373. Min Range: -3.5373
Max Act: 3.4903. Min Act: -0.1700
Data Index: 7676497 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5373. Min Range: -3.5373
Max Act: 3.4746. Min Act: -0.1700
Data Index: 1136980 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5373. Min Range: -3.5373
Max Act: 3.4746. Min Act: -0.1700
Data Index: 2031757 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5373. Min Range: -3.5373
Max Act: 3.4746. Min Act: -0.1700
Data Index: 4799563 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5373. Min Range: -3.5373
Max Act: 3.4746. Min Act: -0.1700
Data Index: 7063678 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5373. Min Range: -3.5373
Max Act: 3.4746. Min Act: -0.1700
Data Index: 4911359 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5373. Min Range: -3.5373
Max Act: 3.4746. Min Act: -0.1700
Data Index: 3579961 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5373. Min Range: -3.5373
Max Act: 3.4433. Min Act: -0.1700
Data Index: 6385359 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5373. Min Range: -3.5373
Max Act: 3.4590. Min Act: -0.1700
Data Index: 6501578 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5373. Min Range: -3.5373
Max Act: 3.4433. Min Act: -0.1700
Data Index: 6293863 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5373. Min Range: -3.5373
Max Act: 3.4590. Min Act: -0.1700
Data Index: 6092009 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5373. Min Range: -3.5373
Max Act: 3.4590. Min Act: -0.1700
Data Index: 4834201 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19