Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4009 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6377. Min Range: -6.6377
Max Act: 6.6377. Min Act: -0.1700
Data Index: 7233189 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6377. Min Range: -6.6377
Max Act: 6.4502. Min Act: -0.1700
Data Index: 2415201 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6377. Min Range: -6.6377
Max Act: 6.4502. Min Act: -0.1700
Data Index: 4350635 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6377. Min Range: -6.6377
Max Act: 6.3877. Min Act: -0.1700
Data Index: 3807853 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6377. Min Range: -6.6377
Max Act: 6.3252. Min Act: -0.1700
Data Index: 764494 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6377. Min Range: -6.6377
Max Act: 6.2627. Min Act: -0.1700
Data Index: 6712896 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6377. Min Range: -6.6377
Max Act: 6.1689. Min Act: -0.1700
Data Index: 6707533 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6377. Min Range: -6.6377
Max Act: 6.1689. Min Act: -0.1700
Data Index: 3715063 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6377. Min Range: -6.6377
Max Act: 6.1689. Min Act: -0.1700
Data Index: 2708310 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6377. Min Range: -6.6377
Max Act: 6.1689. Min Act: -0.1700
Data Index: 5257141 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6377. Min Range: -6.6377
Max Act: 6.0752. Min Act: -0.1700
Data Index: 5129994 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6377. Min Range: -6.6377
Max Act: 6.1064. Min Act: -0.1700
Data Index: 8516708 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6377. Min Range: -6.6377
Max Act: 6.0439. Min Act: -0.1700
Data Index: 6364839 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6377. Min Range: -6.6377
Max Act: 6.0439. Min Act: -0.1700
Data Index: 7194112 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6377. Min Range: -6.6377
Max Act: 6.0439. Min Act: -0.1700
Data Index: 6773577 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6377. Min Range: -6.6377
Max Act: 6.0752. Min Act: -0.1700
Data Index: 5915255 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6377. Min Range: -6.6377
Max Act: 6.0127. Min Act: -0.1700
Data Index: 918021 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6377. Min Range: -6.6377
Max Act: 6.0127. Min Act: -0.1700
Data Index: 2821830 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6377. Min Range: -6.6377
Max Act: 5.9814. Min Act: -0.1700
Data Index: 3371674 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6377. Min Range: -6.6377
Max Act: 5.9502. Min Act: -0.1700
Data Index: 5011631 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19