Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5738 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4839. Min Range: -3.4839
Max Act: 3.4839. Min Act: -0.1700
Data Index: 5944007 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4839. Min Range: -3.4839
Max Act: 3.3742. Min Act: -0.1700
Data Index: 4293761 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4839. Min Range: -3.4839
Max Act: 3.3585. Min Act: -0.1700
Data Index: 4034458 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4839. Min Range: -3.4839
Max Act: 3.3428. Min Act: -0.1700
Data Index: 8618672 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4839. Min Range: -3.4839
Max Act: 3.3428. Min Act: -0.1700
Data Index: 2522693 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4839. Min Range: -3.4839
Max Act: 3.3271. Min Act: -0.1700
Data Index: 6803100 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4839. Min Range: -3.4839
Max Act: 3.2957. Min Act: -0.1700
Data Index: 8126054 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4839. Min Range: -3.4839
Max Act: 3.3114. Min Act: -0.1700
Data Index: 6387039 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4839. Min Range: -3.4839
Max Act: 3.3114. Min Act: -0.1700
Data Index: 4662466 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4839. Min Range: -3.4839
Max Act: 3.2800. Min Act: -0.1700
Data Index: 7766393 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4839. Min Range: -3.4839
Max Act: 3.2800. Min Act: -0.1700
Data Index: 5607077 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4839. Min Range: -3.4839
Max Act: 3.2800. Min Act: -0.1700
Data Index: 5711647 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4839. Min Range: -3.4839
Max Act: 3.2643. Min Act: -0.1700
Data Index: 6558256 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4839. Min Range: -3.4839
Max Act: 3.2329. Min Act: -0.1700
Data Index: 497213 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4839. Min Range: -3.4839
Max Act: 3.2329. Min Act: -0.1700
Data Index: 3173833 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4839. Min Range: -3.4839
Max Act: 3.2329. Min Act: -0.1700
Data Index: 6008498 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4839. Min Range: -3.4839
Max Act: 3.2015. Min Act: -0.1700
Data Index: 1688633 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4839. Min Range: -3.4839
Max Act: 3.2015. Min Act: -0.1700
Data Index: 8401746 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4839. Min Range: -3.4839
Max Act: 3.2015. Min Act: -0.1700
Data Index: 676364 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4839. Min Range: -3.4839
Max Act: 3.2015. Min Act: -0.1700
Data Index: 1685642 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19