Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1736 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.2322. Min Act: -0.1700
Data Index: 2453097 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.2007. Min Act: -0.1700
Data Index: 6068817 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.1535. Min Act: -0.1700
Data Index: 8331964 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.1535. Min Act: -0.1700
Data Index: 6656233 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.1535. Min Act: -0.1700
Data Index: 1906639 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.1220. Min Act: -0.1700
Data Index: 7276121 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.1063. Min Act: -0.1700
Data Index: 2610860 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.1063. Min Act: -0.1700
Data Index: 8331966 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.1063. Min Act: -0.1700
Data Index: 1468043 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.1063. Min Act: -0.1700
Data Index: 510247 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.0905. Min Act: -0.1700
Data Index: 2477067 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.0905. Min Act: -0.1700
Data Index: 995135 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.0905. Min Act: -0.1700
Data Index: 8831137 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.0748. Min Act: -0.1700
Data Index: 1525666 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.0590. Min Act: -0.1700
Data Index: 4578151 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.0748. Min Act: -0.1700
Data Index: 854893 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.0748. Min Act: -0.1700
Data Index: 680836 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.0748. Min Act: -0.1700
Data Index: 1990391 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.0748. Min Act: -0.1700
Data Index: 830468 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2322. Min Range: -3.2322
Max Act: 3.0748. Min Act: -0.1700
Data Index: 740724 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19