Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1329 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2719. Min Range: -6.2719
Max Act: 6.2719. Min Act: -0.1700
Data Index: 4624005 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2719. Min Range: -6.2719
Max Act: 5.9594. Min Act: -0.1700
Data Index: 2427167 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2719. Min Range: -6.2719
Max Act: 5.9594. Min Act: -0.1700
Data Index: 5272213 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2719. Min Range: -6.2719
Max Act: 5.8656. Min Act: -0.1700
Data Index: 6437776 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2719. Min Range: -6.2719
Max Act: 5.8344. Min Act: -0.1700
Data Index: 5555111 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2719. Min Range: -6.2719
Max Act: 5.8031. Min Act: -0.1700
Data Index: 4258948 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2719. Min Range: -6.2719
Max Act: 5.8031. Min Act: -0.1700
Data Index: 6200043 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2719. Min Range: -6.2719
Max Act: 5.7406. Min Act: -0.1700
Data Index: 1661765 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2719. Min Range: -6.2719
Max Act: 5.6469. Min Act: -0.1700
Data Index: 3145413 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2719. Min Range: -6.2719
Max Act: 5.6781. Min Act: -0.1700
Data Index: 4552437 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2719. Min Range: -6.2719
Max Act: 5.6781. Min Act: -0.1700
Data Index: 6673541 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2719. Min Range: -6.2719
Max Act: 5.6781. Min Act: -0.1700
Data Index: 3908345 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2719. Min Range: -6.2719
Max Act: 5.6469. Min Act: -0.1700
Data Index: 6974356 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2719. Min Range: -6.2719
Max Act: 5.6781. Min Act: -0.1700
Data Index: 4820422 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2719. Min Range: -6.2719
Max Act: 5.6156. Min Act: -0.1700
Data Index: 8134956 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2719. Min Range: -6.2719
Max Act: 5.5844. Min Act: -0.1700
Data Index: 1005091 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2719. Min Range: -6.2719
Max Act: 5.5844. Min Act: -0.1700
Data Index: 4255945 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2719. Min Range: -6.2719
Max Act: 5.5844. Min Act: -0.1700
Data Index: 971453 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2719. Min Range: -6.2719
Max Act: 5.5844. Min Act: -0.1700
Data Index: 1885757 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2719. Min Range: -6.2719
Max Act: 5.5844. Min Act: -0.1700
Data Index: 6481605 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19