Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 677 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2954. Min Range: -4.2954
Max Act: 4.2954. Min Act: -0.1700
Data Index: 862469 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2954. Min Range: -4.2954
Max Act: 4.2329. Min Act: -0.1700
Data Index: 1043713 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2954. Min Range: -4.2954
Max Act: 4.2016. Min Act: -0.1700
Data Index: 6398305 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2954. Min Range: -4.2954
Max Act: 4.1391. Min Act: -0.1700
Data Index: 881568 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2954. Min Range: -4.2954
Max Act: 4.1704. Min Act: -0.1700
Data Index: 7465265 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2954. Min Range: -4.2954
Max Act: 4.0766. Min Act: -0.1700
Data Index: 7410768 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2954. Min Range: -4.2954
Max Act: 4.1079. Min Act: -0.1700
Data Index: 4603797 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2954. Min Range: -4.2954
Max Act: 4.0766. Min Act: -0.1700
Data Index: 6885437 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2954. Min Range: -4.2954
Max Act: 4.0454. Min Act: -0.1700
Data Index: 6343557 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2954. Min Range: -4.2954
Max Act: 4.0766. Min Act: -0.1700
Data Index: 4649712 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2954. Min Range: -4.2954
Max Act: 4.0454. Min Act: -0.1700
Data Index: 4173477 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2954. Min Range: -4.2954
Max Act: 4.0141. Min Act: -0.1700
Data Index: 373041 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2954. Min Range: -4.2954
Max Act: 4.0141. Min Act: -0.1700
Data Index: 4873515 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2954. Min Range: -4.2954
Max Act: 4.0141. Min Act: -0.1700
Data Index: 1722466 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2954. Min Range: -4.2954
Max Act: 3.9516. Min Act: -0.1700
Data Index: 3865019 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2954. Min Range: -4.2954
Max Act: 3.9828. Min Act: -0.1700
Data Index: 471954 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2954. Min Range: -4.2954
Max Act: 3.9828. Min Act: -0.1700
Data Index: 3154800 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2954. Min Range: -4.2954
Max Act: 3.9828. Min Act: -0.1700
Data Index: 3335793 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2954. Min Range: -4.2954
Max Act: 3.9828. Min Act: -0.1700
Data Index: 6452725 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2954. Min Range: -4.2954
Max Act: 3.9828. Min Act: -0.1700
Data Index: 160689 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19