Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 125 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2141. Min Range: -9.2141
Max Act: 9.2141. Min Act: -0.1700
Data Index: 2394978 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2141. Min Range: -9.2141
Max Act: 8.6516. Min Act: -0.1700
Data Index: 4116408 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2141. Min Range: -9.2141
Max Act: 8.5266. Min Act: -0.1700
Data Index: 8198450 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2141. Min Range: -9.2141
Max Act: 8.5266. Min Act: -0.1700
Data Index: 6397216 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2141. Min Range: -9.2141
Max Act: 8.4016. Min Act: -0.1700
Data Index: 228504 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2141. Min Range: -9.2141
Max Act: 8.4016. Min Act: -0.1700
Data Index: 6973611 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2141. Min Range: -9.2141
Max Act: 8.3391. Min Act: -0.1700
Data Index: 5178239 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2141. Min Range: -9.2141
Max Act: 8.2766. Min Act: -0.1700
Data Index: 1637076 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2141. Min Range: -9.2141
Max Act: 8.2766. Min Act: -0.1700
Data Index: 2767282 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2141. Min Range: -9.2141
Max Act: 8.3391. Min Act: -0.1700
Data Index: 5006969 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2141. Min Range: -9.2141
Max Act: 8.2766. Min Act: -0.1700
Data Index: 2499193 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2141. Min Range: -9.2141
Max Act: 8.2141. Min Act: -0.1700
Data Index: 6280889 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2141. Min Range: -9.2141
Max Act: 8.2141. Min Act: -0.1700
Data Index: 3532485 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2141. Min Range: -9.2141
Max Act: 8.2141. Min Act: -0.1700
Data Index: 1270223 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2141. Min Range: -9.2141
Max Act: 8.2141. Min Act: -0.1700
Data Index: 8340029 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2141. Min Range: -9.2141
Max Act: 8.1516. Min Act: -0.1700
Data Index: 7433409 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2141. Min Range: -9.2141
Max Act: 8.1516. Min Act: -0.1700
Data Index: 1266342 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2141. Min Range: -9.2141
Max Act: 8.1516. Min Act: -0.1700
Data Index: 8216426 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2141. Min Range: -9.2141
Max Act: 8.1516. Min Act: -0.1700
Data Index: 1389679 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2141. Min Range: -9.2141
Max Act: 8.1516. Min Act: -0.1700
Data Index: 913341 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19