Model: None
Dataset: The Pile
Neuron 3828 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 4.1551. Min Range: -4.1551
Max Act: 4.1551. Min Act: -0.1700
Data Index: 4112776 (The Pile)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1551. Min Range: -4.1551
Max Act: 4.0926. Min Act: -0.1700
Data Index: 3981752 (The Pile)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1551. Min Range: -4.1551
Max Act: 4.0613. Min Act: -0.1700
Data Index: 1322437 (The Pile)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1551. Min Range: -4.1551
Max Act: 4.0301. Min Act: -0.1699
Data Index: 8502981 (The Pile)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1551. Min Range: -4.1551
Max Act: 4.0301. Min Act: -0.1700
Data Index: 8802784 (The Pile)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1551. Min Range: -4.1551
Max Act: 4.0301. Min Act: -0.1700
Data Index: 9951740 (The Pile)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.9988. Min Act: -0.1700
Data Index: 3201359 (The Pile)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.9675. Min Act: -0.1700
Data Index: 8268323 (The Pile)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.9519. Min Act: -0.1700
Data Index: 7747116 (The Pile)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.9519. Min Act: -0.1700
Data Index: 1289254 (The Pile)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.9519. Min Act: -0.1700
Data Index: 9914113 (The Pile)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.9050. Min Act: -0.1700
Data Index: 10351132 (The Pile)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.8894. Min Act: -0.1700
Data Index: 6092828 (The Pile)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.8737. Min Act: -0.1700
Data Index: 10321076 (The Pile)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.8737. Min Act: -0.1700
Data Index: 1130656 (The Pile)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.8424. Min Act: -0.1700
Data Index: 6240967 (The Pile)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.8424. Min Act: -0.1700
Data Index: 3754629 (The Pile)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.8424. Min Act: -0.1700
Data Index: 1498612 (The Pile)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.8424. Min Act: -0.1699
Data Index: 2444329 (The Pile)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.8268. Min Act: -0.1700
Data Index: 6593600 (The Pile)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19