Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1342 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3047. Min Range: -6.3047
Max Act: 6.3047. Min Act: -0.1700
Data Index: 1107004 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3047. Min Range: -6.3047
Max Act: 6.1797. Min Act: -0.1700
Data Index: 4243162 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3047. Min Range: -6.3047
Max Act: 6.1172. Min Act: -0.1700
Data Index: 6900033 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3047. Min Range: -6.3047
Max Act: 6.0547. Min Act: -0.1700
Data Index: 3316653 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3047. Min Range: -6.3047
Max Act: 5.8985. Min Act: -0.1700
Data Index: 823682 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3047. Min Range: -6.3047
Max Act: 5.8985. Min Act: -0.1700
Data Index: 8390436 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3047. Min Range: -6.3047
Max Act: 5.8672. Min Act: -0.1700
Data Index: 7183052 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3047. Min Range: -6.3047
Max Act: 5.8672. Min Act: -0.1700
Data Index: 5718215 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3047. Min Range: -6.3047
Max Act: 5.8047. Min Act: -0.1700
Data Index: 1977806 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3047. Min Range: -6.3047
Max Act: 5.7422. Min Act: -0.1700
Data Index: 5429169 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3047. Min Range: -6.3047
Max Act: 5.7735. Min Act: -0.1700
Data Index: 1822333 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3047. Min Range: -6.3047
Max Act: 5.7422. Min Act: -0.1700
Data Index: 6456952 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3047. Min Range: -6.3047
Max Act: 5.7422. Min Act: -0.1700
Data Index: 658463 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3047. Min Range: -6.3047
Max Act: 5.7422. Min Act: -0.1700
Data Index: 5340256 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3047. Min Range: -6.3047
Max Act: 5.7110. Min Act: -0.1700
Data Index: 3200001 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3047. Min Range: -6.3047
Max Act: 5.7110. Min Act: -0.1700
Data Index: 4838356 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3047. Min Range: -6.3047
Max Act: 5.7110. Min Act: -0.1700
Data Index: 3135429 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3047. Min Range: -6.3047
Max Act: 5.6797. Min Act: -0.1700
Data Index: 4796906 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3047. Min Range: -6.3047
Max Act: 5.6797. Min Act: -0.1700
Data Index: 6715640 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3047. Min Range: -6.3047
Max Act: 5.6797. Min Act: -0.1700
Data Index: 6715641 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19