Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4037 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4539. Min Range: -3.4539
Max Act: 3.4539. Min Act: -0.1700
Data Index: 8184242 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4539. Min Range: -3.4539
Max Act: 3.4539. Min Act: -0.1700
Data Index: 6577825 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4539. Min Range: -3.4539
Max Act: 3.3755. Min Act: -0.1700
Data Index: 3921347 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4539. Min Range: -3.4539
Max Act: 3.3284. Min Act: -0.1700
Data Index: 6577829 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4539. Min Range: -3.4539
Max Act: 3.3441. Min Act: -0.1700
Data Index: 3525821 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4539. Min Range: -3.4539
Max Act: 3.2971. Min Act: -0.1700
Data Index: 5348898 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4539. Min Range: -3.4539
Max Act: 3.2499. Min Act: -0.1700
Data Index: 345612 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4539. Min Range: -3.4539
Max Act: 3.2342. Min Act: -0.1700
Data Index: 6765505 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4539. Min Range: -3.4539
Max Act: 3.2185. Min Act: -0.1700
Data Index: 3529336 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4539. Min Range: -3.4539
Max Act: 3.2499. Min Act: -0.1700
Data Index: 54572 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4539. Min Range: -3.4539
Max Act: 3.1871. Min Act: -0.1700
Data Index: 6003569 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4539. Min Range: -3.4539
Max Act: 3.1713. Min Act: -0.1700
Data Index: 819615 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4539. Min Range: -3.4539
Max Act: 3.1556. Min Act: -0.1700
Data Index: 5045861 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4539. Min Range: -3.4539
Max Act: 3.1556. Min Act: -0.1700
Data Index: 8026298 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4539. Min Range: -3.4539
Max Act: 3.1398. Min Act: -0.1700
Data Index: 6043470 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4539. Min Range: -3.4539
Max Act: 3.1241. Min Act: -0.1700
Data Index: 5604845 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4539. Min Range: -3.4539
Max Act: 3.1083. Min Act: -0.1700
Data Index: 522063 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4539. Min Range: -3.4539
Max Act: 3.1241. Min Act: -0.1700
Data Index: 1269721 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4539. Min Range: -3.4539
Max Act: 3.1241. Min Act: -0.1700
Data Index: 7308601 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4539. Min Range: -3.4539
Max Act: 3.1241. Min Act: -0.1700
Data Index: 295126 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19