Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4032 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.4805. Min Act: -0.1700
Data Index: 3204942 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.4180. Min Act: -0.1700
Data Index: 5235579 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.4180. Min Act: -0.1700
Data Index: 389926 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.3867. Min Act: -0.1700
Data Index: 1292754 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.3242. Min Act: -0.1700
Data Index: 4289831 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.2930. Min Act: -0.1700
Data Index: 2039580 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.3555. Min Act: -0.1700
Data Index: 6324362 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.3242. Min Act: -0.1700
Data Index: 1362994 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.3242. Min Act: -0.1700
Data Index: 997443 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.3242. Min Act: -0.1700
Data Index: 42028 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.2930. Min Act: -0.1700
Data Index: 3624667 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.2930. Min Act: -0.1700
Data Index: 5250012 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.2930. Min Act: -0.1700
Data Index: 2065186 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.2930. Min Act: -0.1700
Data Index: 6363297 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.2617. Min Act: -0.1700
Data Index: 6901810 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.2930. Min Act: -0.1700
Data Index: 4033165 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.2305. Min Act: -0.1700
Data Index: 6503829 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.2617. Min Act: -0.1700
Data Index: 1981834 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.1992. Min Act: -0.1700
Data Index: 4899693 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4805. Min Range: -4.4805
Max Act: 4.1992. Min Act: -0.1700
Data Index: 444963 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19