Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3491 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8030. Min Range: -6.8030
Max Act: 6.8030. Min Act: -0.1700
Data Index: 5562329 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8030. Min Range: -6.8030
Max Act: 6.3967. Min Act: -0.1700
Data Index: 5322834 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8030. Min Range: -6.8030
Max Act: 6.3655. Min Act: -0.1700
Data Index: 6874194 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8030. Min Range: -6.8030
Max Act: 6.2717. Min Act: -0.1700
Data Index: 7488065 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8030. Min Range: -6.8030
Max Act: 6.0217. Min Act: -0.1700
Data Index: 2010441 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8030. Min Range: -6.8030
Max Act: 6.0217. Min Act: -0.1700
Data Index: 5511568 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8030. Min Range: -6.8030
Max Act: 6.0217. Min Act: -0.1700
Data Index: 8314152 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8030. Min Range: -6.8030
Max Act: 5.9905. Min Act: -0.1700
Data Index: 6136756 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8030. Min Range: -6.8030
Max Act: 5.9592. Min Act: -0.1700
Data Index: 4108054 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8030. Min Range: -6.8030
Max Act: 5.9280. Min Act: -0.1700
Data Index: 1754382 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8030. Min Range: -6.8030
Max Act: 5.8967. Min Act: -0.1700
Data Index: 6064028 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8030. Min Range: -6.8030
Max Act: 5.8655. Min Act: -0.1700
Data Index: 1671519 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8030. Min Range: -6.8030
Max Act: 5.8655. Min Act: -0.1700
Data Index: 5996770 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8030. Min Range: -6.8030
Max Act: 5.8030. Min Act: -0.1700
Data Index: 5709890 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8030. Min Range: -6.8030
Max Act: 5.8030. Min Act: -0.1700
Data Index: 142454 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8030. Min Range: -6.8030
Max Act: 5.8030. Min Act: -0.1700
Data Index: 5355614 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8030. Min Range: -6.8030
Max Act: 5.7717. Min Act: -0.1700
Data Index: 6296174 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8030. Min Range: -6.8030
Max Act: 5.7717. Min Act: -0.1700
Data Index: 5573906 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8030. Min Range: -6.8030
Max Act: 5.7405. Min Act: -0.1700
Data Index: 336908 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8030. Min Range: -6.8030
Max Act: 5.7405. Min Act: -0.1700
Data Index: 7419628 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19