Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3346 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.6496. Min Act: -0.1700
Data Index: 560303 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.6496. Min Act: -0.1700
Data Index: 7554352 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.6183. Min Act: -0.1700
Data Index: 2434712 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.5246. Min Act: -0.1700
Data Index: 3584024 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.4933. Min Act: -0.1700
Data Index: 7719736 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.4308. Min Act: -0.1700
Data Index: 3130956 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.3371. Min Act: -0.1700
Data Index: 2262405 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.2121. Min Act: -0.1700
Data Index: 5343606 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.2121. Min Act: -0.1700
Data Index: 3408453 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.1808. Min Act: -0.1700
Data Index: 7917096 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.1496. Min Act: -0.1700
Data Index: 5266606 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.1496. Min Act: -0.1700
Data Index: 4082483 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.1496. Min Act: -0.1700
Data Index: 671041 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.1496. Min Act: -0.1700
Data Index: 2523573 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.1183. Min Act: -0.1700
Data Index: 5973357 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.0871. Min Act: -0.1700
Data Index: 2431749 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.0871. Min Act: -0.1700
Data Index: 8170326 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.0871. Min Act: -0.1700
Data Index: 7384922 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.0558. Min Act: -0.1700
Data Index: 7743352 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6496. Min Range: -6.6496
Max Act: 6.0246. Min Act: -0.1700
Data Index: 7882541 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19