Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3482 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1981. Min Range: -4.1981
Max Act: 4.1981. Min Act: -0.1700
Data Index: 6742720 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1981. Min Range: -4.1981
Max Act: 4.1669. Min Act: -0.1700
Data Index: 83746 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1981. Min Range: -4.1981
Max Act: 4.0418. Min Act: -0.1700
Data Index: 5156979 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1981. Min Range: -4.1981
Max Act: 4.0418. Min Act: -0.1700
Data Index: 2532966 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1981. Min Range: -4.1981
Max Act: 4.0106. Min Act: -0.1700
Data Index: 6804552 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1981. Min Range: -4.1981
Max Act: 4.0106. Min Act: -0.1700
Data Index: 1910763 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1981. Min Range: -4.1981
Max Act: 3.9793. Min Act: -0.1700
Data Index: 5134443 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1981. Min Range: -4.1981
Max Act: 3.9793. Min Act: -0.1700
Data Index: 1653669 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1981. Min Range: -4.1981
Max Act: 3.9481. Min Act: -0.1700
Data Index: 8630923 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1981. Min Range: -4.1981
Max Act: 3.9481. Min Act: -0.1700
Data Index: 4052357 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1981. Min Range: -4.1981
Max Act: 3.9481. Min Act: -0.1700
Data Index: 7914154 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1981. Min Range: -4.1981
Max Act: 3.9168. Min Act: -0.1700
Data Index: 5588378 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1981. Min Range: -4.1981
Max Act: 3.9481. Min Act: -0.1700
Data Index: 2623831 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1981. Min Range: -4.1981
Max Act: 3.9481. Min Act: -0.1700
Data Index: 7668667 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1981. Min Range: -4.1981
Max Act: 3.9168. Min Act: -0.1700
Data Index: 4926246 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1981. Min Range: -4.1981
Max Act: 3.9168. Min Act: -0.1700
Data Index: 2934351 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1981. Min Range: -4.1981
Max Act: 3.8855. Min Act: -0.1700
Data Index: 1034365 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1981. Min Range: -4.1981
Max Act: 3.8855. Min Act: -0.1700
Data Index: 2237703 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1981. Min Range: -4.1981
Max Act: 3.8855. Min Act: -0.1700
Data Index: 4950908 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1981. Min Range: -4.1981
Max Act: 3.8855. Min Act: -0.1700
Data Index: 6420121 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19