Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1811 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0538. Min Range: -7.0538
Max Act: 7.0538. Min Act: -0.1700
Data Index: 4657819 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0538. Min Range: -7.0538
Max Act: 6.9913. Min Act: -0.1700
Data Index: 6776352 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0538. Min Range: -7.0538
Max Act: 6.9600. Min Act: -0.1700
Data Index: 1051423 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0538. Min Range: -7.0538
Max Act: 6.9288. Min Act: -0.1700
Data Index: 182880 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0538. Min Range: -7.0538
Max Act: 6.8663. Min Act: -0.1700
Data Index: 3158588 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0538. Min Range: -7.0538
Max Act: 6.7413. Min Act: -0.1700
Data Index: 4817969 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0538. Min Range: -7.0538
Max Act: 6.7100. Min Act: -0.1700
Data Index: 3870804 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0538. Min Range: -7.0538
Max Act: 6.7413. Min Act: -0.1700
Data Index: 4484178 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0538. Min Range: -7.0538
Max Act: 6.7100. Min Act: -0.1700
Data Index: 2849932 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0538. Min Range: -7.0538
Max Act: 6.7100. Min Act: -0.1700
Data Index: 1523800 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0538. Min Range: -7.0538
Max Act: 6.6788. Min Act: -0.1700
Data Index: 1957859 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0538. Min Range: -7.0538
Max Act: 6.6788. Min Act: -0.1700
Data Index: 6089941 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0538. Min Range: -7.0538
Max Act: 6.6475. Min Act: -0.1700
Data Index: 7145823 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0538. Min Range: -7.0538
Max Act: 6.6475. Min Act: -0.1700
Data Index: 1087003 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0538. Min Range: -7.0538
Max Act: 6.6475. Min Act: -0.1700
Data Index: 6221592 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0538. Min Range: -7.0538
Max Act: 6.6475. Min Act: -0.1700
Data Index: 3158589 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0538. Min Range: -7.0538
Max Act: 6.6163. Min Act: -0.1700
Data Index: 2836948 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0538. Min Range: -7.0538
Max Act: 6.6163. Min Act: -0.1700
Data Index: 882776 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0538. Min Range: -7.0538
Max Act: 6.6163. Min Act: -0.1700
Data Index: 1751992 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0538. Min Range: -7.0538
Max Act: 6.6163. Min Act: -0.1700
Data Index: 1830644 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19