Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2816 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.6704. Min Range: -7.6704
Max Act: 7.6704. Min Act: -0.1700
Data Index: 4545122 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6704. Min Range: -7.6704
Max Act: 7.6704. Min Act: -0.1699
Data Index: 7986394 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6704. Min Range: -7.6704
Max Act: 7.4204. Min Act: -0.1700
Data Index: 2019704 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6704. Min Range: -7.6704
Max Act: 7.3266. Min Act: -0.1700
Data Index: 7072929 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6704. Min Range: -7.6704
Max Act: 7.2954. Min Act: -0.1700
Data Index: 6344243 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6704. Min Range: -7.6704
Max Act: 7.2641. Min Act: -0.1700
Data Index: 2242618 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6704. Min Range: -7.6704
Max Act: 7.2641. Min Act: -0.1700
Data Index: 4741075 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6704. Min Range: -7.6704
Max Act: 7.2329. Min Act: -0.1700
Data Index: 3120007 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6704. Min Range: -7.6704
Max Act: 7.2016. Min Act: -0.1700
Data Index: 379822 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6704. Min Range: -7.6704
Max Act: 7.2016. Min Act: -0.1700
Data Index: 898156 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6704. Min Range: -7.6704
Max Act: 7.2329. Min Act: -0.1700
Data Index: 590111 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6704. Min Range: -7.6704
Max Act: 7.1079. Min Act: -0.1700
Data Index: 415469 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6704. Min Range: -7.6704
Max Act: 7.1391. Min Act: -0.1700
Data Index: 256372 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6704. Min Range: -7.6704
Max Act: 7.1704. Min Act: -0.1700
Data Index: 5848857 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6704. Min Range: -7.6704
Max Act: 7.1391. Min Act: -0.1700
Data Index: 82716 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6704. Min Range: -7.6704
Max Act: 7.1079. Min Act: -0.1700
Data Index: 7072928 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6704. Min Range: -7.6704
Max Act: 7.0766. Min Act: -0.1700
Data Index: 7484218 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6704. Min Range: -7.6704
Max Act: 7.0766. Min Act: -0.1700
Data Index: 5136697 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6704. Min Range: -7.6704
Max Act: 7.0766. Min Act: -0.1700
Data Index: 8576311 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6704. Min Range: -7.6704
Max Act: 7.0454. Min Act: -0.1700
Data Index: 5617996 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19