Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3071 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7516. Min Range: -7.7516
Max Act: 7.7516. Min Act: -0.1700
Data Index: 5043530 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7516. Min Range: -7.7516
Max Act: 7.7516. Min Act: -0.1700
Data Index: 1574470 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7516. Min Range: -7.7516
Max Act: 7.6891. Min Act: -0.1700
Data Index: 4312851 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7516. Min Range: -7.7516
Max Act: 7.5016. Min Act: -0.1700
Data Index: 3700073 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7516. Min Range: -7.7516
Max Act: 7.3766. Min Act: -0.1700
Data Index: 5044243 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7516. Min Range: -7.7516
Max Act: 7.3766. Min Act: -0.1700
Data Index: 3567366 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7516. Min Range: -7.7516
Max Act: 7.3766. Min Act: -0.1700
Data Index: 7308085 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7516. Min Range: -7.7516
Max Act: 7.3453. Min Act: -0.1700
Data Index: 272054 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7516. Min Range: -7.7516
Max Act: 7.3141. Min Act: -0.1700
Data Index: 2094934 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7516. Min Range: -7.7516
Max Act: 7.3141. Min Act: -0.1700
Data Index: 5204986 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7516. Min Range: -7.7516
Max Act: 7.2828. Min Act: -0.1700
Data Index: 8345153 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7516. Min Range: -7.7516
Max Act: 7.2828. Min Act: -0.1700
Data Index: 1091872 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7516. Min Range: -7.7516
Max Act: 7.2516. Min Act: -0.1700
Data Index: 2043130 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7516. Min Range: -7.7516
Max Act: 7.2203. Min Act: -0.1700
Data Index: 5021029 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7516. Min Range: -7.7516
Max Act: 7.1891. Min Act: -0.1700
Data Index: 3399838 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7516. Min Range: -7.7516
Max Act: 7.2203. Min Act: -0.1700
Data Index: 675659 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7516. Min Range: -7.7516
Max Act: 7.2203. Min Act: -0.1700
Data Index: 5853582 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7516. Min Range: -7.7516
Max Act: 7.1891. Min Act: -0.1700
Data Index: 7387777 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7516. Min Range: -7.7516
Max Act: 7.2203. Min Act: -0.1700
Data Index: 2683478 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7516. Min Range: -7.7516
Max Act: 7.1578. Min Act: -0.1700
Data Index: 7695237 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19