Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4984 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8665. Min Range: -8.8665
Max Act: 8.8665. Min Act: -0.1700
Data Index: 5677122 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8665. Min Range: -8.8665
Max Act: 8.4915. Min Act: -0.1700
Data Index: 5316369 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8665. Min Range: -8.8665
Max Act: 8.3978. Min Act: -0.1700
Data Index: 6701912 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8665. Min Range: -8.8665
Max Act: 8.3353. Min Act: -0.1700
Data Index: 2560573 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8665. Min Range: -8.8665
Max Act: 8.2415. Min Act: -0.1700
Data Index: 7099562 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8665. Min Range: -8.8665
Max Act: 8.1790. Min Act: -0.1700
Data Index: 1661619 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8665. Min Range: -8.8665
Max Act: 8.1790. Min Act: -0.1700
Data Index: 5677123 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8665. Min Range: -8.8665
Max Act: 8.1478. Min Act: -0.1700
Data Index: 4520643 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8665. Min Range: -8.8665
Max Act: 8.1165. Min Act: -0.1700
Data Index: 1121127 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8665. Min Range: -8.8665
Max Act: 8.0853. Min Act: -0.1700
Data Index: 1317623 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8665. Min Range: -8.8665
Max Act: 8.0540. Min Act: -0.1700
Data Index: 8501507 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8665. Min Range: -8.8665
Max Act: 8.0228. Min Act: -0.1700
Data Index: 7431991 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8665. Min Range: -8.8665
Max Act: 7.9915. Min Act: -0.1700
Data Index: 8475637 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8665. Min Range: -8.8665
Max Act: 8.0228. Min Act: -0.1700
Data Index: 1505461 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8665. Min Range: -8.8665
Max Act: 7.9603. Min Act: -0.1700
Data Index: 7911632 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8665. Min Range: -8.8665
Max Act: 7.9603. Min Act: -0.1700
Data Index: 1647559 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8665. Min Range: -8.8665
Max Act: 7.9603. Min Act: -0.1700
Data Index: 6010632 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8665. Min Range: -8.8665
Max Act: 7.9603. Min Act: -0.1700
Data Index: 2003069 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8665. Min Range: -8.8665
Max Act: 7.9290. Min Act: -0.1700
Data Index: 4368783 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8665. Min Range: -8.8665
Max Act: 7.8978. Min Act: -0.1700
Data Index: 2449085 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19