Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1910 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4489. Min Range: -8.4489
Max Act: 8.4489. Min Act: -0.1700
Data Index: 8665993 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4489. Min Range: -8.4489
Max Act: 7.9489. Min Act: -0.1700
Data Index: 4127527 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4489. Min Range: -8.4489
Max Act: 7.8239. Min Act: -0.1700
Data Index: 2648139 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4489. Min Range: -8.4489
Max Act: 7.8239. Min Act: -0.1700
Data Index: 3179387 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4489. Min Range: -8.4489
Max Act: 7.6989. Min Act: -0.1700
Data Index: 3321988 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4489. Min Range: -8.4489
Max Act: 7.6989. Min Act: -0.1700
Data Index: 3289361 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4489. Min Range: -8.4489
Max Act: 7.6989. Min Act: -0.1700
Data Index: 1132370 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4489. Min Range: -8.4489
Max Act: 7.6364. Min Act: -0.1700
Data Index: 6254551 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4489. Min Range: -8.4489
Max Act: 7.5426. Min Act: -0.1700
Data Index: 4605768 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4489. Min Range: -8.4489
Max Act: 7.5114. Min Act: -0.1700
Data Index: 7859680 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4489. Min Range: -8.4489
Max Act: 7.4801. Min Act: -0.1700
Data Index: 5217491 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4489. Min Range: -8.4489
Max Act: 7.4801. Min Act: -0.1700
Data Index: 5158267 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4489. Min Range: -8.4489
Max Act: 7.4489. Min Act: -0.1700
Data Index: 8514931 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4489. Min Range: -8.4489
Max Act: 7.4489. Min Act: -0.1700
Data Index: 4437780 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4489. Min Range: -8.4489
Max Act: 7.4489. Min Act: -0.1700
Data Index: 7901063 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4489. Min Range: -8.4489
Max Act: 7.4176. Min Act: -0.1700
Data Index: 3893848 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4489. Min Range: -8.4489
Max Act: 7.3864. Min Act: -0.1700
Data Index: 2944336 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4489. Min Range: -8.4489
Max Act: 7.4176. Min Act: -0.1700
Data Index: 6524883 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4489. Min Range: -8.4489
Max Act: 7.4176. Min Act: -0.1700
Data Index: 7104953 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4489. Min Range: -8.4489
Max Act: 7.3864. Min Act: -0.1700
Data Index: 6361055 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19