Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5356 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4992. Min Range: -5.4992
Max Act: 5.4992. Min Act: -0.1700
Data Index: 7996114 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4992. Min Range: -5.4992
Max Act: 5.3117. Min Act: -0.1700
Data Index: 8641159 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4992. Min Range: -5.4992
Max Act: 5.2492. Min Act: -0.1700
Data Index: 3700499 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4992. Min Range: -5.4992
Max Act: 5.2180. Min Act: -0.1700
Data Index: 5244936 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4992. Min Range: -5.4992
Max Act: 5.1867. Min Act: -0.1700
Data Index: 706243 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4992. Min Range: -5.4992
Max Act: 5.1555. Min Act: -0.1700
Data Index: 1313215 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4992. Min Range: -5.4992
Max Act: 5.1555. Min Act: -0.1700
Data Index: 312134 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4992. Min Range: -5.4992
Max Act: 5.1242. Min Act: -0.1700
Data Index: 2750775 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4992. Min Range: -5.4992
Max Act: 5.0617. Min Act: -0.1700
Data Index: 360913 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4992. Min Range: -5.4992
Max Act: 5.0930. Min Act: -0.1700
Data Index: 5889883 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4992. Min Range: -5.4992
Max Act: 5.0930. Min Act: -0.1700
Data Index: 3160330 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4992. Min Range: -5.4992
Max Act: 5.0617. Min Act: -0.1700
Data Index: 663715 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4992. Min Range: -5.4992
Max Act: 5.0617. Min Act: -0.1700
Data Index: 1595613 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4992. Min Range: -5.4992
Max Act: 5.0305. Min Act: -0.1700
Data Index: 7870950 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4992. Min Range: -5.4992
Max Act: 5.0305. Min Act: -0.1700
Data Index: 8236611 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4992. Min Range: -5.4992
Max Act: 5.0305. Min Act: -0.1700
Data Index: 1483800 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4992. Min Range: -5.4992
Max Act: 4.9992. Min Act: -0.1700
Data Index: 6016542 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4992. Min Range: -5.4992
Max Act: 4.9992. Min Act: -0.1700
Data Index: 3322374 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4992. Min Range: -5.4992
Max Act: 4.9680. Min Act: -0.1700
Data Index: 2733922 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4992. Min Range: -5.4992
Max Act: 4.9992. Min Act: -0.1700
Data Index: 3736006 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19