Model: None
Dataset: The Pile
Neuron 834 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.9044. Min Range: -2.9044
Max Act: 2.9044. Min Act: -0.1700
Data Index: 7208987 (The Pile)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9044. Min Range: -2.9044
Max Act: 2.8409. Min Act: -0.1700
Data Index: 8683601 (The Pile)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9044. Min Range: -2.9044
Max Act: 2.8409. Min Act: -0.1700
Data Index: 10072313 (The Pile)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9044. Min Range: -2.9044
Max Act: 2.8568. Min Act: -0.1700
Data Index: 8126535 (The Pile)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9044. Min Range: -2.9044
Max Act: 2.8727. Min Act: -0.1700
Data Index: 765765 (The Pile)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9044. Min Range: -2.9044
Max Act: 2.8568. Min Act: -0.1700
Data Index: 8820229 (The Pile)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9044. Min Range: -2.9044
Max Act: 2.8409. Min Act: -0.1700
Data Index: 2477830 (The Pile)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9044. Min Range: -2.9044
Max Act: 2.8409. Min Act: -0.1700
Data Index: 7715788 (The Pile)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9044. Min Range: -2.9044
Max Act: 2.8568. Min Act: -0.1700
Data Index: 2375989 (The Pile)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9044. Min Range: -2.9044
Max Act: 2.8250. Min Act: -0.1700
Data Index: 3715414 (The Pile)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9044. Min Range: -2.9044
Max Act: 2.8250. Min Act: -0.1700
Data Index: 5844237 (The Pile)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9044. Min Range: -2.9044
Max Act: 2.8250. Min Act: -0.1700
Data Index: 7726425 (The Pile)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9044. Min Range: -2.9044
Max Act: 2.8250. Min Act: -0.1700
Data Index: 4409571 (The Pile)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9044. Min Range: -2.9044
Max Act: 2.8091. Min Act: -0.1700
Data Index: 1122278 (The Pile)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9044. Min Range: -2.9044
Max Act: 2.8250. Min Act: -0.1700
Data Index: 4598817 (The Pile)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9044. Min Range: -2.9044
Max Act: 2.8250. Min Act: -0.1700
Data Index: 2400576 (The Pile)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9044. Min Range: -2.9044
Max Act: 2.8091. Min Act: -0.1700
Data Index: 4957745 (The Pile)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9044. Min Range: -2.9044
Max Act: 2.7931. Min Act: -0.1700
Data Index: 1826204 (The Pile)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9044. Min Range: -2.9044
Max Act: 2.8250. Min Act: -0.1700
Data Index: 1649558 (The Pile)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9044. Min Range: -2.9044
Max Act: 2.8091. Min Act: -0.1700
Data Index: 8627428 (The Pile)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19