Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4530 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2725. Min Range: -4.2725
Max Act: 4.2725. Min Act: -0.1700
Data Index: 3085525 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2725. Min Range: -4.2725
Max Act: 4.1787. Min Act: -0.1700
Data Index: 6609857 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2725. Min Range: -4.2725
Max Act: 4.1162. Min Act: -0.1700
Data Index: 6362459 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2725. Min Range: -4.2725
Max Act: 4.1162. Min Act: -0.1700
Data Index: 7039368 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2725. Min Range: -4.2725
Max Act: 4.0537. Min Act: -0.1700
Data Index: 4161398 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2725. Min Range: -4.2725
Max Act: 3.9912. Min Act: -0.1700
Data Index: 2080060 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2725. Min Range: -4.2725
Max Act: 4.0224. Min Act: -0.1700
Data Index: 6457777 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2725. Min Range: -4.2725
Max Act: 4.0224. Min Act: -0.1700
Data Index: 59480 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2725. Min Range: -4.2725
Max Act: 4.0224. Min Act: -0.1700
Data Index: 1556188 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2725. Min Range: -4.2725
Max Act: 3.9912. Min Act: -0.1700
Data Index: 132215 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2725. Min Range: -4.2725
Max Act: 3.9912. Min Act: -0.1700
Data Index: 2587482 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2725. Min Range: -4.2725
Max Act: 3.9912. Min Act: -0.1700
Data Index: 5125509 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2725. Min Range: -4.2725
Max Act: 3.9912. Min Act: -0.1700
Data Index: 2853881 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2725. Min Range: -4.2725
Max Act: 3.9912. Min Act: -0.1700
Data Index: 943563 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2725. Min Range: -4.2725
Max Act: 3.9599. Min Act: -0.1700
Data Index: 5726649 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2725. Min Range: -4.2725
Max Act: 3.9599. Min Act: -0.1700
Data Index: 8810806 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2725. Min Range: -4.2725
Max Act: 3.9599. Min Act: -0.1700
Data Index: 4527736 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2725. Min Range: -4.2725
Max Act: 3.9599. Min Act: -0.1700
Data Index: 5803088 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2725. Min Range: -4.2725
Max Act: 3.9599. Min Act: -0.1700
Data Index: 5633767 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2725. Min Range: -4.2725
Max Act: 3.9599. Min Act: -0.1700
Data Index: 825154 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19