Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4016 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4905. Min Range: -7.4905
Max Act: 7.4905. Min Act: -0.1700
Data Index: 8296850 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4905. Min Range: -7.4905
Max Act: 7.3655. Min Act: -0.1700
Data Index: 4413657 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4905. Min Range: -7.4905
Max Act: 7.3655. Min Act: -0.1700
Data Index: 6585874 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4905. Min Range: -7.4905
Max Act: 7.3655. Min Act: -0.1700
Data Index: 8721042 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4905. Min Range: -7.4905
Max Act: 7.3655. Min Act: -0.1700
Data Index: 8128220 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4905. Min Range: -7.4905
Max Act: 7.2717. Min Act: -0.1700
Data Index: 1403454 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4905. Min Range: -7.4905
Max Act: 7.2405. Min Act: -0.1700
Data Index: 795084 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4905. Min Range: -7.4905
Max Act: 7.2405. Min Act: -0.1700
Data Index: 4565940 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4905. Min Range: -7.4905
Max Act: 7.1780. Min Act: -0.1700
Data Index: 1601387 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4905. Min Range: -7.4905
Max Act: 7.1780. Min Act: -0.1700
Data Index: 5121351 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4905. Min Range: -7.4905
Max Act: 7.1780. Min Act: -0.1700
Data Index: 1708241 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4905. Min Range: -7.4905
Max Act: 7.1467. Min Act: -0.1700
Data Index: 481538 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4905. Min Range: -7.4905
Max Act: 7.1780. Min Act: -0.1700
Data Index: 7739930 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4905. Min Range: -7.4905
Max Act: 7.1467. Min Act: -0.1700
Data Index: 8276707 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4905. Min Range: -7.4905
Max Act: 7.1467. Min Act: -0.1700
Data Index: 8729740 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4905. Min Range: -7.4905
Max Act: 7.1467. Min Act: -0.1700
Data Index: 5503615 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4905. Min Range: -7.4905
Max Act: 7.1155. Min Act: -0.1700
Data Index: 8287238 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4905. Min Range: -7.4905
Max Act: 7.1155. Min Act: -0.1700
Data Index: 591934 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4905. Min Range: -7.4905
Max Act: 7.0842. Min Act: -0.1700
Data Index: 4022878 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4905. Min Range: -7.4905
Max Act: 7.0842. Min Act: -0.1700
Data Index: 250777 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19