Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3060 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9949. Min Range: -6.9949
Max Act: 6.9949. Min Act: -0.1700
Data Index: 5814048 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9949. Min Range: -6.9949
Max Act: 6.8387. Min Act: -0.1700
Data Index: 7205386 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9949. Min Range: -6.9949
Max Act: 6.8074. Min Act: -0.1700
Data Index: 4953979 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9949. Min Range: -6.9949
Max Act: 6.7762. Min Act: -0.1700
Data Index: 8545977 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9949. Min Range: -6.9949
Max Act: 6.7762. Min Act: -0.1700
Data Index: 3387933 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9949. Min Range: -6.9949
Max Act: 6.7762. Min Act: -0.1700
Data Index: 4616942 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9949. Min Range: -6.9949
Max Act: 6.7449. Min Act: -0.1700
Data Index: 4043958 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9949. Min Range: -6.9949
Max Act: 6.7449. Min Act: -0.1700
Data Index: 3633462 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9949. Min Range: -6.9949
Max Act: 6.7137. Min Act: -0.1700
Data Index: 8609753 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9949. Min Range: -6.9949
Max Act: 6.7449. Min Act: -0.1700
Data Index: 445384 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9949. Min Range: -6.9949
Max Act: 6.7137. Min Act: -0.1700
Data Index: 3796831 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9949. Min Range: -6.9949
Max Act: 6.7137. Min Act: -0.1700
Data Index: 7084444 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9949. Min Range: -6.9949
Max Act: 6.7137. Min Act: -0.1700
Data Index: 3324556 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9949. Min Range: -6.9949
Max Act: 6.6824. Min Act: -0.1700
Data Index: 2362179 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9949. Min Range: -6.9949
Max Act: 6.6824. Min Act: -0.1700
Data Index: 8433494 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9949. Min Range: -6.9949
Max Act: 6.6824. Min Act: -0.1700
Data Index: 3834812 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9949. Min Range: -6.9949
Max Act: 6.6824. Min Act: -0.1700
Data Index: 4726629 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9949. Min Range: -6.9949
Max Act: 6.6824. Min Act: -0.1700
Data Index: 4249772 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9949. Min Range: -6.9949
Max Act: 6.6824. Min Act: -0.1700
Data Index: 237112 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9949. Min Range: -6.9949
Max Act: 6.6824. Min Act: -0.1700
Data Index: 891326 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19