Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2052 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8731. Min Range: -4.8731
Max Act: 4.8731. Min Act: -0.1700
Data Index: 2636843 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8731. Min Range: -4.8731
Max Act: 4.8418. Min Act: -0.1700
Data Index: 7301911 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8731. Min Range: -4.8731
Max Act: 4.8106. Min Act: -0.1700
Data Index: 1971607 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8731. Min Range: -4.8731
Max Act: 4.8106. Min Act: -0.1700
Data Index: 3970267 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8731. Min Range: -4.8731
Max Act: 4.7793. Min Act: -0.1700
Data Index: 8778165 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8731. Min Range: -4.8731
Max Act: 4.7481. Min Act: -0.1700
Data Index: 4891725 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8731. Min Range: -4.8731
Max Act: 4.7481. Min Act: -0.1700
Data Index: 8521541 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8731. Min Range: -4.8731
Max Act: 4.7481. Min Act: -0.1700
Data Index: 2450856 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8731. Min Range: -4.8731
Max Act: 4.7168. Min Act: -0.1700
Data Index: 5970808 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8731. Min Range: -4.8731
Max Act: 4.7168. Min Act: -0.1700
Data Index: 648707 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8731. Min Range: -4.8731
Max Act: 4.7168. Min Act: -0.1700
Data Index: 3357189 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8731. Min Range: -4.8731
Max Act: 4.6856. Min Act: -0.1700
Data Index: 1760413 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8731. Min Range: -4.8731
Max Act: 4.6856. Min Act: -0.1700
Data Index: 6506032 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8731. Min Range: -4.8731
Max Act: 4.6856. Min Act: -0.1700
Data Index: 1946236 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8731. Min Range: -4.8731
Max Act: 4.6543. Min Act: -0.1700
Data Index: 7861640 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8731. Min Range: -4.8731
Max Act: 4.6543. Min Act: -0.1700
Data Index: 8672187 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8731. Min Range: -4.8731
Max Act: 4.6543. Min Act: -0.1700
Data Index: 2655009 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8731. Min Range: -4.8731
Max Act: 4.6543. Min Act: -0.1700
Data Index: 1932441 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8731. Min Range: -4.8731
Max Act: 4.6543. Min Act: -0.1700
Data Index: 899379 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8731. Min Range: -4.8731
Max Act: 4.6543. Min Act: -0.1700
Data Index: 7449600 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19