Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4715 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0986. Min Range: -6.0986
Max Act: 6.0986. Min Act: -0.1700
Data Index: 256234 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0986. Min Range: -6.0986
Max Act: 6.0361. Min Act: -0.1700
Data Index: 2440424 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0986. Min Range: -6.0986
Max Act: 6.0361. Min Act: -0.1700
Data Index: 8638293 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0986. Min Range: -6.0986
Max Act: 6.0049. Min Act: -0.1700
Data Index: 6203816 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0986. Min Range: -6.0986
Max Act: 6.0049. Min Act: -0.1700
Data Index: 1569454 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.9736. Min Act: -0.1700
Data Index: 780435 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.9424. Min Act: -0.1700
Data Index: 6310911 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.9111. Min Act: -0.1700
Data Index: 2617304 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.7861. Min Act: -0.1700
Data Index: 6557576 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.7549. Min Act: -0.1700
Data Index: 6325103 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.7549. Min Act: -0.1700
Data Index: 8382514 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.7236. Min Act: -0.1700
Data Index: 6612793 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.6924. Min Act: -0.1700
Data Index: 1749152 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.6924. Min Act: -0.1700
Data Index: 2783253 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.6611. Min Act: -0.1700
Data Index: 7219691 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.6611. Min Act: -0.1700
Data Index: 4348165 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.6611. Min Act: -0.1700
Data Index: 5130174 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.6611. Min Act: -0.1700
Data Index: 8802729 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.5986. Min Act: -0.1700
Data Index: 74523 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0986. Min Range: -6.0986
Max Act: 5.5674. Min Act: -0.1700
Data Index: 4151865 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19