Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4820 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8459. Min Range: -5.8459
Max Act: 5.8459. Min Act: -0.1700
Data Index: 5934419 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8459. Min Range: -5.8459
Max Act: 5.5959. Min Act: -0.1700
Data Index: 1037250 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8459. Min Range: -5.8459
Max Act: 5.5646. Min Act: -0.1700
Data Index: 453113 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8459. Min Range: -5.8459
Max Act: 4.7209. Min Act: -0.1700
Data Index: 4575225 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8459. Min Range: -5.8459
Max Act: 4.6896. Min Act: -0.1700
Data Index: 4572441 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8459. Min Range: -5.8459
Max Act: 4.6896. Min Act: -0.1700
Data Index: 5171940 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8459. Min Range: -5.8459
Max Act: 4.5959. Min Act: -0.1700
Data Index: 783449 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8459. Min Range: -5.8459
Max Act: 4.5021. Min Act: -0.1700
Data Index: 1217823 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8459. Min Range: -5.8459
Max Act: 4.4709. Min Act: -0.1700
Data Index: 2617213 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8459. Min Range: -5.8459
Max Act: 4.4709. Min Act: -0.1700
Data Index: 8407249 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8459. Min Range: -5.8459
Max Act: 4.4709. Min Act: -0.1700
Data Index: 7577256 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8459. Min Range: -5.8459
Max Act: 4.4709. Min Act: -0.1700
Data Index: 1256274 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8459. Min Range: -5.8459
Max Act: 4.4709. Min Act: -0.1700
Data Index: 1325739 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8459. Min Range: -5.8459
Max Act: 4.4709. Min Act: -0.1700
Data Index: 7716454 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8459. Min Range: -5.8459
Max Act: 4.4396. Min Act: -0.1700
Data Index: 8385930 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8459. Min Range: -5.8459
Max Act: 4.4396. Min Act: -0.1700
Data Index: 5564152 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8459. Min Range: -5.8459
Max Act: 4.4396. Min Act: -0.1700
Data Index: 4239087 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8459. Min Range: -5.8459
Max Act: 4.4396. Min Act: -0.1700
Data Index: 647987 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8459. Min Range: -5.8459
Max Act: 4.3771. Min Act: -0.1700
Data Index: 7344603 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8459. Min Range: -5.8459
Max Act: 4.4084. Min Act: -0.1700
Data Index: 5706108 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19