Model: None
Dataset: The Pile
Neuron 795 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.2497. Min Range: -2.2497
Max Act: 2.2497. Min Act: -0.1700
Data Index: 7700632 (The Pile)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2497. Min Range: -2.2497
Max Act: 2.2497. Min Act: -0.1700
Data Index: 5613240 (The Pile)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2497. Min Range: -2.2497
Max Act: 2.2332. Min Act: -0.1699
Data Index: 5489816 (The Pile)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2497. Min Range: -2.2497
Max Act: 2.2415. Min Act: -0.1700
Data Index: 3835179 (The Pile)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2497. Min Range: -2.2497
Max Act: 2.2084. Min Act: -0.1699
Data Index: 2728129 (The Pile)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2497. Min Range: -2.2497
Max Act: 2.2001. Min Act: -0.1700
Data Index: 6783110 (The Pile)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2497. Min Range: -2.2497
Max Act: 2.1918. Min Act: -0.1699
Data Index: 2725347 (The Pile)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2497. Min Range: -2.2497
Max Act: 2.2415. Min Act: -0.1700
Data Index: 6352179 (The Pile)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2497. Min Range: -2.2497
Max Act: 2.2084. Min Act: -0.1699
Data Index: 3721280 (The Pile)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2497. Min Range: -2.2497
Max Act: 2.2001. Min Act: -0.1700
Data Index: 10753322 (The Pile)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2497. Min Range: -2.2497
Max Act: 2.1835. Min Act: -0.1700
Data Index: 5288425 (The Pile)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2497. Min Range: -2.2497
Max Act: 2.1835. Min Act: -0.1700
Data Index: 4324635 (The Pile)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2497. Min Range: -2.2497
Max Act: 2.1752. Min Act: -0.1700
Data Index: 6086743 (The Pile)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2497. Min Range: -2.2497
Max Act: 2.1835. Min Act: -0.1700
Data Index: 3171557 (The Pile)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2497. Min Range: -2.2497
Max Act: 2.1585. Min Act: -0.1699
Data Index: 2122936 (The Pile)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2497. Min Range: -2.2497
Max Act: 2.1918. Min Act: -0.1700
Data Index: 1145405 (The Pile)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2497. Min Range: -2.2497
Max Act: 2.1669. Min Act: -0.1700
Data Index: 2355448 (The Pile)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2497. Min Range: -2.2497
Max Act: 2.1419. Min Act: -0.1700
Data Index: 5266641 (The Pile)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2497. Min Range: -2.2497
Max Act: 2.1252. Min Act: -0.1699
Data Index: 10194060 (The Pile)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2497. Min Range: -2.2497
Max Act: 2.1419. Min Act: -0.1700
Data Index: 3930412 (The Pile)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19