Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1845 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.2984. Min Range: -8.2984
Max Act: 8.2984. Min Act: -0.1700
Data Index: 1843792 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2984. Min Range: -8.2984
Max Act: 8.2984. Min Act: -0.1700
Data Index: 4506312 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2984. Min Range: -8.2984
Max Act: 8.2359. Min Act: -0.1700
Data Index: 4936708 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2984. Min Range: -8.2984
Max Act: 8.0484. Min Act: -0.1700
Data Index: 1404738 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2984. Min Range: -8.2984
Max Act: 8.0484. Min Act: -0.1700
Data Index: 5900831 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2984. Min Range: -8.2984
Max Act: 7.9859. Min Act: -0.1700
Data Index: 2280785 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2984. Min Range: -8.2984
Max Act: 7.9859. Min Act: -0.1700
Data Index: 2840777 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2984. Min Range: -8.2984
Max Act: 7.9234. Min Act: -0.1700
Data Index: 6640754 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2984. Min Range: -8.2984
Max Act: 7.9234. Min Act: -0.1700
Data Index: 300951 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2984. Min Range: -8.2984
Max Act: 7.8921. Min Act: -0.1700
Data Index: 6738888 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2984. Min Range: -8.2984
Max Act: 7.8296. Min Act: -0.1700
Data Index: 2789838 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2984. Min Range: -8.2984
Max Act: 7.8296. Min Act: -0.1700
Data Index: 6355197 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2984. Min Range: -8.2984
Max Act: 7.8609. Min Act: -0.1700
Data Index: 3080387 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2984. Min Range: -8.2984
Max Act: 7.8296. Min Act: -0.1700
Data Index: 6904029 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2984. Min Range: -8.2984
Max Act: 7.7984. Min Act: -0.1700
Data Index: 4366993 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2984. Min Range: -8.2984
Max Act: 7.7984. Min Act: -0.1700
Data Index: 3588898 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2984. Min Range: -8.2984
Max Act: 7.7984. Min Act: -0.1700
Data Index: 8127258 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2984. Min Range: -8.2984
Max Act: 7.8296. Min Act: -0.1700
Data Index: 673286 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2984. Min Range: -8.2984
Max Act: 7.7359. Min Act: -0.1700
Data Index: 7087144 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2984. Min Range: -8.2984
Max Act: 7.7359. Min Act: -0.1700
Data Index: 3670436 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19