Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4926 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7775. Min Range: -5.7775
Max Act: 5.7775. Min Act: -0.1700
Data Index: 5500353 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7775. Min Range: -5.7775
Max Act: 5.3400. Min Act: -0.1700
Data Index: 3919198 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7775. Min Range: -5.7775
Max Act: 5.3088. Min Act: -0.1700
Data Index: 1233209 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7775. Min Range: -5.7775
Max Act: 5.2463. Min Act: -0.1700
Data Index: 6565351 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7775. Min Range: -5.7775
Max Act: 5.1838. Min Act: -0.1700
Data Index: 6842018 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7775. Min Range: -5.7775
Max Act: 5.1838. Min Act: -0.1700
Data Index: 3969623 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7775. Min Range: -5.7775
Max Act: 5.2150. Min Act: -0.1700
Data Index: 7447555 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7775. Min Range: -5.7775
Max Act: 5.0900. Min Act: -0.1700
Data Index: 4909287 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7775. Min Range: -5.7775
Max Act: 5.1213. Min Act: -0.1700
Data Index: 1386976 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7775. Min Range: -5.7775
Max Act: 5.0900. Min Act: -0.1700
Data Index: 1494556 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7775. Min Range: -5.7775
Max Act: 5.0588. Min Act: -0.1700
Data Index: 4635293 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7775. Min Range: -5.7775
Max Act: 5.0900. Min Act: -0.1700
Data Index: 2134070 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7775. Min Range: -5.7775
Max Act: 5.0275. Min Act: -0.1700
Data Index: 970679 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7775. Min Range: -5.7775
Max Act: 5.0275. Min Act: -0.1700
Data Index: 7876415 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7775. Min Range: -5.7775
Max Act: 5.0275. Min Act: -0.1700
Data Index: 1490008 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7775. Min Range: -5.7775
Max Act: 4.9650. Min Act: -0.1700
Data Index: 5971953 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7775. Min Range: -5.7775
Max Act: 4.9025. Min Act: -0.1700
Data Index: 6869383 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7775. Min Range: -5.7775
Max Act: 4.9025. Min Act: -0.1700
Data Index: 3028426 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7775. Min Range: -5.7775
Max Act: 4.9338. Min Act: -0.1700
Data Index: 60680 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7775. Min Range: -5.7775
Max Act: 4.9338. Min Act: -0.1700
Data Index: 3792092 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19