Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4030 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5555. Min Range: -7.5555
Max Act: 7.5555. Min Act: -0.1700
Data Index: 3188916 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5555. Min Range: -7.5555
Max Act: 6.7430. Min Act: -0.1700
Data Index: 3429803 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5555. Min Range: -7.5555
Max Act: 6.6492. Min Act: -0.1700
Data Index: 5468136 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5555. Min Range: -7.5555
Max Act: 6.6180. Min Act: -0.1700
Data Index: 4244006 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5555. Min Range: -7.5555
Max Act: 6.5867. Min Act: -0.1700
Data Index: 3290206 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5555. Min Range: -7.5555
Max Act: 6.5555. Min Act: -0.1700
Data Index: 6586295 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5555. Min Range: -7.5555
Max Act: 6.5555. Min Act: -0.1700
Data Index: 6992558 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5555. Min Range: -7.5555
Max Act: 6.5555. Min Act: -0.1700
Data Index: 4149243 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5555. Min Range: -7.5555
Max Act: 6.4930. Min Act: -0.1700
Data Index: 1121949 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5555. Min Range: -7.5555
Max Act: 6.5242. Min Act: -0.1700
Data Index: 1420651 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5555. Min Range: -7.5555
Max Act: 6.4617. Min Act: -0.1700
Data Index: 7624143 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5555. Min Range: -7.5555
Max Act: 6.4305. Min Act: -0.1700
Data Index: 6169116 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5555. Min Range: -7.5555
Max Act: 6.4305. Min Act: -0.1700
Data Index: 3280247 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5555. Min Range: -7.5555
Max Act: 6.4305. Min Act: -0.1700
Data Index: 3865738 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5555. Min Range: -7.5555
Max Act: 6.3992. Min Act: -0.1700
Data Index: 4244005 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5555. Min Range: -7.5555
Max Act: 6.3992. Min Act: -0.1700
Data Index: 1976278 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5555. Min Range: -7.5555
Max Act: 6.3992. Min Act: -0.1700
Data Index: 4155301 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5555. Min Range: -7.5555
Max Act: 6.3680. Min Act: -0.1700
Data Index: 6169113 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5555. Min Range: -7.5555
Max Act: 6.3680. Min Act: -0.1700
Data Index: 6594530 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5555. Min Range: -7.5555
Max Act: 6.3992. Min Act: -0.1700
Data Index: 157367 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19