Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4844 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0116. Min Range: -6.0116
Max Act: 6.0116. Min Act: -0.1700
Data Index: 3441568 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0116. Min Range: -6.0116
Max Act: 5.9178. Min Act: -0.1700
Data Index: 3157895 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0116. Min Range: -6.0116
Max Act: 5.8553. Min Act: -0.1700
Data Index: 5339486 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0116. Min Range: -6.0116
Max Act: 5.8553. Min Act: -0.1700
Data Index: 3152173 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0116. Min Range: -6.0116
Max Act: 5.7616. Min Act: -0.1700
Data Index: 8305823 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0116. Min Range: -6.0116
Max Act: 5.7303. Min Act: -0.1700
Data Index: 1541469 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0116. Min Range: -6.0116
Max Act: 5.6991. Min Act: -0.1700
Data Index: 132085 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0116. Min Range: -6.0116
Max Act: 5.6991. Min Act: -0.1700
Data Index: 2286041 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0116. Min Range: -6.0116
Max Act: 5.6991. Min Act: -0.1700
Data Index: 1278086 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0116. Min Range: -6.0116
Max Act: 5.6991. Min Act: -0.1700
Data Index: 8163682 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0116. Min Range: -6.0116
Max Act: 5.6678. Min Act: -0.1700
Data Index: 3512425 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0116. Min Range: -6.0116
Max Act: 5.6678. Min Act: -0.1700
Data Index: 6213937 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0116. Min Range: -6.0116
Max Act: 5.6678. Min Act: -0.1700
Data Index: 5863082 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0116. Min Range: -6.0116
Max Act: 5.6366. Min Act: -0.1700
Data Index: 226839 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0116. Min Range: -6.0116
Max Act: 5.6053. Min Act: -0.1700
Data Index: 317259 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0116. Min Range: -6.0116
Max Act: 5.6678. Min Act: -0.1700
Data Index: 8067425 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0116. Min Range: -6.0116
Max Act: 5.6366. Min Act: -0.1700
Data Index: 3679062 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0116. Min Range: -6.0116
Max Act: 5.6053. Min Act: -0.1700
Data Index: 2394274 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0116. Min Range: -6.0116
Max Act: 5.6053. Min Act: -0.1700
Data Index: 4349864 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0116. Min Range: -6.0116
Max Act: 5.5741. Min Act: -0.1700
Data Index: 5979360 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #19