Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3901 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0541. Min Range: -5.0541
Max Act: 5.0541. Min Act: -0.1700
Data Index: 4007507 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0541. Min Range: -5.0541
Max Act: 4.9291. Min Act: -0.1700
Data Index: 7662150 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0541. Min Range: -5.0541
Max Act: 4.8979. Min Act: -0.1700
Data Index: 1515272 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0541. Min Range: -5.0541
Max Act: 4.9604. Min Act: -0.1700
Data Index: 5735645 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0541. Min Range: -5.0541
Max Act: 4.8979. Min Act: -0.1700
Data Index: 7457389 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0541. Min Range: -5.0541
Max Act: 4.8354. Min Act: -0.1700
Data Index: 1869902 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0541. Min Range: -5.0541
Max Act: 4.8354. Min Act: -0.1700
Data Index: 6356540 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0541. Min Range: -5.0541
Max Act: 4.8354. Min Act: -0.1700
Data Index: 1443505 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0541. Min Range: -5.0541
Max Act: 4.8041. Min Act: -0.1700
Data Index: 7957222 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0541. Min Range: -5.0541
Max Act: 4.7729. Min Act: -0.1700
Data Index: 4252399 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0541. Min Range: -5.0541
Max Act: 4.7729. Min Act: -0.1700
Data Index: 8320574 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0541. Min Range: -5.0541
Max Act: 4.7729. Min Act: -0.1700
Data Index: 1674704 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0541. Min Range: -5.0541
Max Act: 4.7729. Min Act: -0.1700
Data Index: 8342073 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0541. Min Range: -5.0541
Max Act: 4.7416. Min Act: -0.1700
Data Index: 2024199 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0541. Min Range: -5.0541
Max Act: 4.7104. Min Act: -0.1700
Data Index: 8264075 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0541. Min Range: -5.0541
Max Act: 4.7104. Min Act: -0.1700
Data Index: 1419766 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0541. Min Range: -5.0541
Max Act: 4.6479. Min Act: -0.1700
Data Index: 3421126 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0541. Min Range: -5.0541
Max Act: 4.6791. Min Act: -0.1700
Data Index: 8181450 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0541. Min Range: -5.0541
Max Act: 4.6791. Min Act: -0.1700
Data Index: 5238667 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0541. Min Range: -5.0541
Max Act: 4.6791. Min Act: -0.1700
Data Index: 5202933 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19