Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3878 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6516. Min Range: -4.6516
Max Act: 4.6516. Min Act: -0.1700
Data Index: 1921561 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6516. Min Range: -4.6516
Max Act: 4.5891. Min Act: -0.1700
Data Index: 5799707 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6516. Min Range: -4.6516
Max Act: 4.5891. Min Act: -0.1700
Data Index: 934613 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6516. Min Range: -4.6516
Max Act: 4.5578. Min Act: -0.1700
Data Index: 7672637 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6516. Min Range: -4.6516
Max Act: 4.5578. Min Act: -0.1700
Data Index: 6951483 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6516. Min Range: -4.6516
Max Act: 4.5266. Min Act: -0.1700
Data Index: 706115 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6516. Min Range: -4.6516
Max Act: 4.4953. Min Act: -0.1700
Data Index: 5058766 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6516. Min Range: -4.6516
Max Act: 4.5266. Min Act: -0.1700
Data Index: 3505665 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6516. Min Range: -4.6516
Max Act: 4.4641. Min Act: -0.1700
Data Index: 410037 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6516. Min Range: -4.6516
Max Act: 4.4641. Min Act: -0.1700
Data Index: 8681525 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6516. Min Range: -4.6516
Max Act: 4.4641. Min Act: -0.1700
Data Index: 4127986 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6516. Min Range: -4.6516
Max Act: 4.4641. Min Act: -0.1700
Data Index: 853643 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6516. Min Range: -4.6516
Max Act: 4.4328. Min Act: -0.1700
Data Index: 6183895 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6516. Min Range: -4.6516
Max Act: 4.4328. Min Act: -0.1700
Data Index: 609581 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6516. Min Range: -4.6516
Max Act: 4.4328. Min Act: -0.1700
Data Index: 5466475 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6516. Min Range: -4.6516
Max Act: 4.4328. Min Act: -0.1700
Data Index: 783254 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6516. Min Range: -4.6516
Max Act: 4.3703. Min Act: -0.1700
Data Index: 7380915 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6516. Min Range: -4.6516
Max Act: 4.4016. Min Act: -0.1700
Data Index: 7558860 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6516. Min Range: -4.6516
Max Act: 4.4016. Min Act: -0.1700
Data Index: 1465919 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6516. Min Range: -4.6516
Max Act: 4.4016. Min Act: -0.1700
Data Index: 4573331 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19