Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6374 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1675. Min Range: -8.1675
Max Act: 8.1675. Min Act: -0.1700
Data Index: 75985 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1675. Min Range: -8.1675
Max Act: 8.0738. Min Act: -0.1700
Data Index: 2450078 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1675. Min Range: -8.1675
Max Act: 8.0113. Min Act: -0.1700
Data Index: 4566619 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1675. Min Range: -8.1675
Max Act: 7.9175. Min Act: -0.1700
Data Index: 742566 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1675. Min Range: -8.1675
Max Act: 7.8863. Min Act: -0.1700
Data Index: 2579320 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1675. Min Range: -8.1675
Max Act: 7.8550. Min Act: -0.1700
Data Index: 7722660 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1675. Min Range: -8.1675
Max Act: 7.7925. Min Act: -0.1700
Data Index: 4459366 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1675. Min Range: -8.1675
Max Act: 7.7925. Min Act: -0.1700
Data Index: 7387486 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1675. Min Range: -8.1675
Max Act: 7.7925. Min Act: -0.1700
Data Index: 4323939 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1675. Min Range: -8.1675
Max Act: 7.7613. Min Act: -0.1700
Data Index: 7920783 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1675. Min Range: -8.1675
Max Act: 7.7300. Min Act: -0.1700
Data Index: 8145613 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1675. Min Range: -8.1675
Max Act: 7.6988. Min Act: -0.1700
Data Index: 7539662 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1675. Min Range: -8.1675
Max Act: 7.6675. Min Act: -0.1700
Data Index: 5498563 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1675. Min Range: -8.1675
Max Act: 7.6675. Min Act: -0.1700
Data Index: 351635 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1675. Min Range: -8.1675
Max Act: 7.6050. Min Act: -0.1700
Data Index: 4114619 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1675. Min Range: -8.1675
Max Act: 7.6363. Min Act: -0.1700
Data Index: 5845944 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1675. Min Range: -8.1675
Max Act: 7.5738. Min Act: -0.1700
Data Index: 936302 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1675. Min Range: -8.1675
Max Act: 7.5425. Min Act: -0.1700
Data Index: 8143887 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1675. Min Range: -8.1675
Max Act: 7.5425. Min Act: -0.1700
Data Index: 879222 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1675. Min Range: -8.1675
Max Act: 7.5113. Min Act: -0.1700
Data Index: 3335462 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19