Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3418 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1690. Min Range: -8.1690
Max Act: 8.1690. Min Act: -0.1700
Data Index: 4096900 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1690. Min Range: -8.1690
Max Act: 7.7627. Min Act: -0.1700
Data Index: 6319582 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1690. Min Range: -8.1690
Max Act: 7.7315. Min Act: -0.1700
Data Index: 7428928 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1690. Min Range: -8.1690
Max Act: 7.6377. Min Act: -0.1700
Data Index: 7380444 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1690. Min Range: -8.1690
Max Act: 7.6377. Min Act: -0.1700
Data Index: 5129813 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1690. Min Range: -8.1690
Max Act: 7.5752. Min Act: -0.1700
Data Index: 6189211 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1690. Min Range: -8.1690
Max Act: 7.5440. Min Act: -0.1700
Data Index: 3172821 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1690. Min Range: -8.1690
Max Act: 7.5752. Min Act: -0.1700
Data Index: 6638502 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1690. Min Range: -8.1690
Max Act: 7.5440. Min Act: -0.1700
Data Index: 7158898 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1690. Min Range: -8.1690
Max Act: 7.4502. Min Act: -0.1700
Data Index: 7639822 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1690. Min Range: -8.1690
Max Act: 7.4815. Min Act: -0.1700
Data Index: 6064957 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1690. Min Range: -8.1690
Max Act: 7.4815. Min Act: -0.1700
Data Index: 6891654 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1690. Min Range: -8.1690
Max Act: 7.4502. Min Act: -0.1700
Data Index: 4084405 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1690. Min Range: -8.1690
Max Act: 7.4502. Min Act: -0.1700
Data Index: 8267762 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1690. Min Range: -8.1690
Max Act: 7.4190. Min Act: -0.1700
Data Index: 1900813 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1690. Min Range: -8.1690
Max Act: 7.3877. Min Act: -0.1700
Data Index: 703976 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1690. Min Range: -8.1690
Max Act: 7.3877. Min Act: -0.1700
Data Index: 3386168 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1690. Min Range: -8.1690
Max Act: 7.3565. Min Act: -0.1700
Data Index: 1288191 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1690. Min Range: -8.1690
Max Act: 7.3252. Min Act: -0.1700
Data Index: 6684959 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1690. Min Range: -8.1690
Max Act: 7.3252. Min Act: -0.1700
Data Index: 4697748 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19