Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3850 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2955. Min Range: -8.2955
Max Act: 8.2955. Min Act: -0.1700
Data Index: 3249229 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2955. Min Range: -8.2955
Max Act: 7.9205. Min Act: -0.1700
Data Index: 7635406 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2955. Min Range: -8.2955
Max Act: 7.9205. Min Act: -0.1700
Data Index: 8251530 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2955. Min Range: -8.2955
Max Act: 7.8580. Min Act: -0.1700
Data Index: 4600071 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2955. Min Range: -8.2955
Max Act: 7.8580. Min Act: -0.1700
Data Index: 626735 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2955. Min Range: -8.2955
Max Act: 7.8580. Min Act: -0.1700
Data Index: 3610200 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2955. Min Range: -8.2955
Max Act: 7.8580. Min Act: -0.1700
Data Index: 2971574 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2955. Min Range: -8.2955
Max Act: 7.8580. Min Act: -0.1700
Data Index: 8234755 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2955. Min Range: -8.2955
Max Act: 7.8580. Min Act: -0.1700
Data Index: 4078947 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2955. Min Range: -8.2955
Max Act: 7.7955. Min Act: -0.1700
Data Index: 4726549 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2955. Min Range: -8.2955
Max Act: 7.7330. Min Act: -0.1700
Data Index: 4288132 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2955. Min Range: -8.2955
Max Act: 7.7955. Min Act: -0.1700
Data Index: 7881561 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2955. Min Range: -8.2955
Max Act: 7.7955. Min Act: -0.1700
Data Index: 5747464 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2955. Min Range: -8.2955
Max Act: 7.7955. Min Act: -0.1700
Data Index: 6942201 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2955. Min Range: -8.2955
Max Act: 7.7330. Min Act: -0.1700
Data Index: 5730951 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2955. Min Range: -8.2955
Max Act: 7.7330. Min Act: -0.1700
Data Index: 5908865 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2955. Min Range: -8.2955
Max Act: 7.7330. Min Act: -0.1700
Data Index: 2544627 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2955. Min Range: -8.2955
Max Act: 7.7330. Min Act: -0.1700
Data Index: 7496105 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2955. Min Range: -8.2955
Max Act: 7.7330. Min Act: -0.1700
Data Index: 6037508 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2955. Min Range: -8.2955
Max Act: 7.7018. Min Act: -0.1700
Data Index: 3586895 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19