Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6277 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1633. Min Range: -9.1633
Max Act: 9.1633. Min Act: -0.1700
Data Index: 6147921 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1633. Min Range: -9.1633
Max Act: 9.0383. Min Act: -0.1700
Data Index: 5117896 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1633. Min Range: -9.1633
Max Act: 8.9758. Min Act: -0.1700
Data Index: 5186763 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1633. Min Range: -9.1633
Max Act: 8.9133. Min Act: -0.1700
Data Index: 7877877 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1633. Min Range: -9.1633
Max Act: 8.8508. Min Act: -0.1700
Data Index: 3761754 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1633. Min Range: -9.1633
Max Act: 8.7883. Min Act: -0.1700
Data Index: 8578821 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1633. Min Range: -9.1633
Max Act: 8.7883. Min Act: -0.1700
Data Index: 4271712 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1633. Min Range: -9.1633
Max Act: 8.7883. Min Act: -0.1700
Data Index: 3381944 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1633. Min Range: -9.1633
Max Act: 8.7883. Min Act: -0.1700
Data Index: 904073 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1633. Min Range: -9.1633
Max Act: 8.7883. Min Act: -0.1700
Data Index: 6802464 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1633. Min Range: -9.1633
Max Act: 8.7883. Min Act: -0.1700
Data Index: 32475 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1633. Min Range: -9.1633
Max Act: 8.7258. Min Act: -0.1700
Data Index: 1979737 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1633. Min Range: -9.1633
Max Act: 8.7258. Min Act: -0.1700
Data Index: 3419977 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1633. Min Range: -9.1633
Max Act: 8.7258. Min Act: -0.1700
Data Index: 8303372 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1633. Min Range: -9.1633
Max Act: 8.7258. Min Act: -0.1700
Data Index: 5422314 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1633. Min Range: -9.1633
Max Act: 8.7258. Min Act: -0.1700
Data Index: 3828839 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1633. Min Range: -9.1633
Max Act: 8.6633. Min Act: -0.1700
Data Index: 5683825 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1633. Min Range: -9.1633
Max Act: 8.6633. Min Act: -0.1700
Data Index: 1251484 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1633. Min Range: -9.1633
Max Act: 8.6008. Min Act: -0.1700
Data Index: 2515756 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1633. Min Range: -9.1633
Max Act: 8.6633. Min Act: -0.1700
Data Index: 1037807 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19