Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6284 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6555. Min Range: -4.6555
Max Act: 4.6555. Min Act: -0.1700
Data Index: 643819 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6555. Min Range: -4.6555
Max Act: 4.4992. Min Act: -0.1700
Data Index: 1948774 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6555. Min Range: -4.6555
Max Act: 4.4992. Min Act: -0.1700
Data Index: 3020916 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6555. Min Range: -4.6555
Max Act: 4.4992. Min Act: -0.1700
Data Index: 7951882 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6555. Min Range: -4.6555
Max Act: 4.4367. Min Act: -0.1700
Data Index: 5374656 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6555. Min Range: -4.6555
Max Act: 4.4680. Min Act: -0.1700
Data Index: 4283831 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6555. Min Range: -4.6555
Max Act: 4.4367. Min Act: -0.1700
Data Index: 1127681 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6555. Min Range: -4.6555
Max Act: 4.4680. Min Act: -0.1700
Data Index: 5046429 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6555. Min Range: -4.6555
Max Act: 4.3742. Min Act: -0.1700
Data Index: 4218300 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6555. Min Range: -4.6555
Max Act: 4.4055. Min Act: -0.1700
Data Index: 4983757 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6555. Min Range: -4.6555
Max Act: 4.3742. Min Act: -0.1700
Data Index: 191375 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6555. Min Range: -4.6555
Max Act: 4.3742. Min Act: -0.1700
Data Index: 7899749 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6555. Min Range: -4.6555
Max Act: 4.3742. Min Act: -0.1700
Data Index: 2405887 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6555. Min Range: -4.6555
Max Act: 4.4055. Min Act: -0.1700
Data Index: 4889927 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6555. Min Range: -4.6555
Max Act: 4.3430. Min Act: -0.1700
Data Index: 208766 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6555. Min Range: -4.6555
Max Act: 4.3117. Min Act: -0.1700
Data Index: 1264409 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6555. Min Range: -4.6555
Max Act: 4.3117. Min Act: -0.1700
Data Index: 448555 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6555. Min Range: -4.6555
Max Act: 4.3117. Min Act: -0.1700
Data Index: 1786211 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6555. Min Range: -4.6555
Max Act: 4.2805. Min Act: -0.1700
Data Index: 3446853 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6555. Min Range: -4.6555
Max Act: 4.3117. Min Act: -0.1700
Data Index: 903307 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19