Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2014 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6395. Min Range: -7.6395
Max Act: 7.6395. Min Act: -0.1700
Data Index: 4184439 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6395. Min Range: -7.6395
Max Act: 7.1708. Min Act: -0.1700
Data Index: 840773 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6395. Min Range: -7.6395
Max Act: 7.1083. Min Act: -0.1700
Data Index: 7413616 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6395. Min Range: -7.6395
Max Act: 6.9208. Min Act: -0.1700
Data Index: 57951 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6395. Min Range: -7.6395
Max Act: 6.8895. Min Act: -0.1700
Data Index: 4102443 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6395. Min Range: -7.6395
Max Act: 6.8583. Min Act: -0.1700
Data Index: 4955518 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6395. Min Range: -7.6395
Max Act: 6.8583. Min Act: -0.1700
Data Index: 3954988 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6395. Min Range: -7.6395
Max Act: 6.8583. Min Act: -0.1700
Data Index: 5235676 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6395. Min Range: -7.6395
Max Act: 6.8270. Min Act: -0.1700
Data Index: 755096 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6395. Min Range: -7.6395
Max Act: 6.7645. Min Act: -0.1700
Data Index: 4084002 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6395. Min Range: -7.6395
Max Act: 6.7333. Min Act: -0.1700
Data Index: 2595799 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6395. Min Range: -7.6395
Max Act: 6.7020. Min Act: -0.1700
Data Index: 7593972 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6395. Min Range: -7.6395
Max Act: 6.7020. Min Act: -0.1700
Data Index: 4892243 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6395. Min Range: -7.6395
Max Act: 6.6708. Min Act: -0.1700
Data Index: 6290614 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6395. Min Range: -7.6395
Max Act: 6.6708. Min Act: -0.1700
Data Index: 2703795 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6395. Min Range: -7.6395
Max Act: 6.6395. Min Act: -0.1700
Data Index: 7539292 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6395. Min Range: -7.6395
Max Act: 6.6395. Min Act: -0.1700
Data Index: 7152972 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6395. Min Range: -7.6395
Max Act: 6.6083. Min Act: -0.1700
Data Index: 5487668 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6395. Min Range: -7.6395
Max Act: 6.5770. Min Act: -0.1700
Data Index: 6994550 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6395. Min Range: -7.6395
Max Act: 6.6083. Min Act: -0.1700
Data Index: 4012565 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19