Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2071 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6165. Min Range: -6.6165
Max Act: 6.6165. Min Act: -0.1700
Data Index: 2644294 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6165. Min Range: -6.6165
Max Act: 6.5540. Min Act: -0.1700
Data Index: 4478965 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6165. Min Range: -6.6165
Max Act: 6.5540. Min Act: -0.1700
Data Index: 5320841 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6165. Min Range: -6.6165
Max Act: 6.4603. Min Act: -0.1700
Data Index: 1059725 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6165. Min Range: -6.6165
Max Act: 6.3665. Min Act: -0.1700
Data Index: 2222746 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6165. Min Range: -6.6165
Max Act: 6.3665. Min Act: -0.1700
Data Index: 7779953 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6165. Min Range: -6.6165
Max Act: 6.3040. Min Act: -0.1699
Data Index: 1816473 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6165. Min Range: -6.6165
Max Act: 6.3353. Min Act: -0.1700
Data Index: 6006929 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6165. Min Range: -6.6165
Max Act: 6.3040. Min Act: -0.1700
Data Index: 5256166 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6165. Min Range: -6.6165
Max Act: 6.2728. Min Act: -0.1700
Data Index: 1973652 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6165. Min Range: -6.6165
Max Act: 6.2728. Min Act: -0.1700
Data Index: 1861679 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6165. Min Range: -6.6165
Max Act: 6.2103. Min Act: -0.1700
Data Index: 786308 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6165. Min Range: -6.6165
Max Act: 6.2103. Min Act: -0.1700
Data Index: 8203543 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6165. Min Range: -6.6165
Max Act: 6.2103. Min Act: -0.1700
Data Index: 3948344 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6165. Min Range: -6.6165
Max Act: 6.1790. Min Act: -0.1700
Data Index: 1305113 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6165. Min Range: -6.6165
Max Act: 6.2103. Min Act: -0.1700
Data Index: 5829544 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6165. Min Range: -6.6165
Max Act: 6.2103. Min Act: -0.1700
Data Index: 8637115 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6165. Min Range: -6.6165
Max Act: 6.1790. Min Act: -0.1700
Data Index: 7533804 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6165. Min Range: -6.6165
Max Act: 6.1478. Min Act: -0.1700
Data Index: 1282899 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6165. Min Range: -6.6165
Max Act: 6.1478. Min Act: -0.1700
Data Index: 6494807 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19