Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2708 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.8891. Min Act: -0.1700
Data Index: 8214302 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.6079. Min Act: -0.1700
Data Index: 1193594 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.5454. Min Act: -0.1700
Data Index: 1917829 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.5454. Min Act: -0.1700
Data Index: 925181 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.5141. Min Act: -0.1700
Data Index: 3010496 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.4516. Min Act: -0.1700
Data Index: 2482533 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.4516. Min Act: -0.1700
Data Index: 6077561 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.4516. Min Act: -0.1700
Data Index: 7331426 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.3579. Min Act: -0.1700
Data Index: 3889546 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.3266. Min Act: -0.1700
Data Index: 5491999 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.3579. Min Act: -0.1700
Data Index: 4193880 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.2954. Min Act: -0.1700
Data Index: 8591404 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.2954. Min Act: -0.1700
Data Index: 2911900 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.2641. Min Act: -0.1700
Data Index: 1812525 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.2641. Min Act: -0.1700
Data Index: 8712286 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.2954. Min Act: -0.1700
Data Index: 5621718 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.2329. Min Act: -0.1700
Data Index: 1071933 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.2329. Min Act: -0.1700
Data Index: 4647567 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.2016. Min Act: -0.1700
Data Index: 8675695 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8891. Min Range: -7.8891
Max Act: 7.2016. Min Act: -0.1700
Data Index: 768588 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19