Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4860 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9003. Min Range: -6.9003
Max Act: 6.9003. Min Act: -0.1700
Data Index: 5648610 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9003. Min Range: -6.9003
Max Act: 6.8690. Min Act: -0.1700
Data Index: 433418 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9003. Min Range: -6.9003
Max Act: 6.7440. Min Act: -0.1700
Data Index: 1977311 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9003. Min Range: -6.9003
Max Act: 6.5565. Min Act: -0.1700
Data Index: 669669 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9003. Min Range: -6.9003
Max Act: 6.5565. Min Act: -0.1700
Data Index: 4839348 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9003. Min Range: -6.9003
Max Act: 6.5253. Min Act: -0.1700
Data Index: 8161519 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9003. Min Range: -6.9003
Max Act: 6.4315. Min Act: -0.1700
Data Index: 5770865 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9003. Min Range: -6.9003
Max Act: 6.4315. Min Act: -0.1700
Data Index: 2001160 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9003. Min Range: -6.9003
Max Act: 6.4003. Min Act: -0.1700
Data Index: 785412 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9003. Min Range: -6.9003
Max Act: 6.4003. Min Act: -0.1700
Data Index: 3468491 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9003. Min Range: -6.9003
Max Act: 6.4315. Min Act: -0.1700
Data Index: 15996 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9003. Min Range: -6.9003
Max Act: 6.4003. Min Act: -0.1700
Data Index: 770919 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9003. Min Range: -6.9003
Max Act: 6.3378. Min Act: -0.1700
Data Index: 3462932 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9003. Min Range: -6.9003
Max Act: 6.2753. Min Act: -0.1700
Data Index: 1454957 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9003. Min Range: -6.9003
Max Act: 6.2753. Min Act: -0.1700
Data Index: 5034389 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9003. Min Range: -6.9003
Max Act: 6.2753. Min Act: -0.1700
Data Index: 2272886 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9003. Min Range: -6.9003
Max Act: 6.2440. Min Act: -0.1700
Data Index: 7549842 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9003. Min Range: -6.9003
Max Act: 6.1503. Min Act: -0.1700
Data Index: 4425101 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9003. Min Range: -6.9003
Max Act: 6.1815. Min Act: -0.1700
Data Index: 4336048 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9003. Min Range: -6.9003
Max Act: 6.1815. Min Act: -0.1700
Data Index: 3946811 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19