Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2008 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.9169. Min Act: -0.1700
Data Index: 8338892 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.9482. Min Act: -0.1700
Data Index: 8338912 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.9169. Min Act: -0.1700
Data Index: 3952756 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.8857. Min Act: -0.1700
Data Index: 8529166 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.8544. Min Act: -0.1700
Data Index: 8338904 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.8544. Min Act: -0.1700
Data Index: 1787758 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.8544. Min Act: -0.1700
Data Index: 4236304 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.7919. Min Act: -0.1700
Data Index: 6135810 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.7607. Min Act: -0.1700
Data Index: 108213 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.7919. Min Act: -0.1700
Data Index: 424822 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.7607. Min Act: -0.1700
Data Index: 1787760 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.7607. Min Act: -0.1700
Data Index: 1787751 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.7294. Min Act: -0.1700
Data Index: 1787750 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.6982. Min Act: -0.1700
Data Index: 5018694 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.6982. Min Act: -0.1700
Data Index: 5798201 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.6357. Min Act: -0.1700
Data Index: 1274006 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.6669. Min Act: -0.1700
Data Index: 3146183 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.6669. Min Act: -0.1700
Data Index: 1787749 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.6669. Min Act: -0.1700
Data Index: 6135814 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9482. Min Range: -4.9482
Max Act: 4.6357. Min Act: -0.1700
Data Index: 1787752 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19