Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1943 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.4971. Min Range: -9.4971
Max Act: 9.4971. Min Act: -0.1700
Data Index: 2612055 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4971. Min Range: -9.4971
Max Act: 9.4346. Min Act: -0.1700
Data Index: 3934097 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4971. Min Range: -9.4971
Max Act: 9.3721. Min Act: -0.1700
Data Index: 1072070 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4971. Min Range: -9.4971
Max Act: 9.3096. Min Act: -0.1700
Data Index: 2561642 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4971. Min Range: -9.4971
Max Act: 9.3096. Min Act: -0.1700
Data Index: 6436596 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4971. Min Range: -9.4971
Max Act: 9.2471. Min Act: -0.1700
Data Index: 2135321 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4971. Min Range: -9.4971
Max Act: 9.2471. Min Act: -0.1700
Data Index: 3458215 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4971. Min Range: -9.4971
Max Act: 9.1846. Min Act: -0.1700
Data Index: 3115728 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4971. Min Range: -9.4971
Max Act: 9.1846. Min Act: -0.1700
Data Index: 4869429 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4971. Min Range: -9.4971
Max Act: 9.1846. Min Act: -0.1700
Data Index: 8465006 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4971. Min Range: -9.4971
Max Act: 9.1221. Min Act: -0.1700
Data Index: 2494980 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4971. Min Range: -9.4971
Max Act: 9.1221. Min Act: -0.1700
Data Index: 3725912 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4971. Min Range: -9.4971
Max Act: 9.0596. Min Act: -0.1700
Data Index: 5005493 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4971. Min Range: -9.4971
Max Act: 9.0596. Min Act: -0.1700
Data Index: 2448299 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4971. Min Range: -9.4971
Max Act: 9.0596. Min Act: -0.1700
Data Index: 5407613 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4971. Min Range: -9.4971
Max Act: 9.0596. Min Act: -0.1700
Data Index: 6193834 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4971. Min Range: -9.4971
Max Act: 9.0596. Min Act: -0.1700
Data Index: 1384975 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4971. Min Range: -9.4971
Max Act: 8.9971. Min Act: -0.1700
Data Index: 4638424 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4971. Min Range: -9.4971
Max Act: 8.9971. Min Act: -0.1700
Data Index: 4856147 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4971. Min Range: -9.4971
Max Act: 8.9346. Min Act: -0.1700
Data Index: 5426321 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19