Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4809 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1839. Min Range: -8.1839
Max Act: 8.1839. Min Act: -0.1700
Data Index: 4120203 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1839. Min Range: -8.1839
Max Act: 7.9339. Min Act: -0.1700
Data Index: 2185345 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1839. Min Range: -8.1839
Max Act: 7.8714. Min Act: -0.1700
Data Index: 386043 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1839. Min Range: -8.1839
Max Act: 7.8089. Min Act: -0.1700
Data Index: 4939321 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1839. Min Range: -8.1839
Max Act: 7.8714. Min Act: -0.1700
Data Index: 5825405 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1839. Min Range: -8.1839
Max Act: 7.7464. Min Act: -0.1700
Data Index: 115815 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1839. Min Range: -8.1839
Max Act: 7.7151. Min Act: -0.1700
Data Index: 681386 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1839. Min Range: -8.1839
Max Act: 7.6839. Min Act: -0.1700
Data Index: 8210595 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1839. Min Range: -8.1839
Max Act: 7.6839. Min Act: -0.1700
Data Index: 1944192 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1839. Min Range: -8.1839
Max Act: 7.6839. Min Act: -0.1700
Data Index: 4903768 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1839. Min Range: -8.1839
Max Act: 7.6526. Min Act: -0.1700
Data Index: 6361527 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1839. Min Range: -8.1839
Max Act: 7.6214. Min Act: -0.1700
Data Index: 1712868 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1839. Min Range: -8.1839
Max Act: 7.6526. Min Act: -0.1700
Data Index: 6995152 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1839. Min Range: -8.1839
Max Act: 7.6214. Min Act: -0.1700
Data Index: 8095736 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1839. Min Range: -8.1839
Max Act: 7.6214. Min Act: -0.1700
Data Index: 3784738 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1839. Min Range: -8.1839
Max Act: 7.5901. Min Act: -0.1700
Data Index: 5260070 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1839. Min Range: -8.1839
Max Act: 7.4964. Min Act: -0.1700
Data Index: 961196 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1839. Min Range: -8.1839
Max Act: 7.4651. Min Act: -0.1700
Data Index: 2247377 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1839. Min Range: -8.1839
Max Act: 7.4651. Min Act: -0.1700
Data Index: 3998099 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1839. Min Range: -8.1839
Max Act: 7.4651. Min Act: -0.1700
Data Index: 572525 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19