Model: None
Dataset: The Pile
Neuron 2123 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 4.2528. Min Range: -4.2528
Max Act: 4.2528. Min Act: -0.1700
Data Index: 10049888 (The Pile)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2528. Min Range: -4.2528
Max Act: 4.2215. Min Act: -0.1700
Data Index: 356388 (The Pile)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2528. Min Range: -4.2528
Max Act: 4.1278. Min Act: -0.1698
Data Index: 3225 (The Pile)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2528. Min Range: -4.2528
Max Act: 4.1278. Min Act: -0.1700
Data Index: 128994 (The Pile)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2528. Min Range: -4.2528
Max Act: 4.1278. Min Act: -0.1699
Data Index: 380821 (The Pile)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2528. Min Range: -4.2528
Max Act: 4.1278. Min Act: -0.1700
Data Index: 107062 (The Pile)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2528. Min Range: -4.2528
Max Act: 4.0965. Min Act: -0.1700
Data Index: 7922031 (The Pile)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2528. Min Range: -4.2528
Max Act: 4.0965. Min Act: -0.1700
Data Index: 6310087 (The Pile)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2528. Min Range: -4.2528
Max Act: 4.0965. Min Act: -0.1700
Data Index: 8640255 (The Pile)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2528. Min Range: -4.2528
Max Act: 4.0965. Min Act: -0.1700
Data Index: 8325123 (The Pile)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2528. Min Range: -4.2528
Max Act: 4.0809. Min Act: -0.1698
Data Index: 7114675 (The Pile)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2528. Min Range: -4.2528
Max Act: 4.0652. Min Act: -0.1700
Data Index: 1768339 (The Pile)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2528. Min Range: -4.2528
Max Act: 4.0496. Min Act: -0.1700
Data Index: 5275722 (The Pile)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2528. Min Range: -4.2528
Max Act: 4.0496. Min Act: -0.1700
Data Index: 8429014 (The Pile)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2528. Min Range: -4.2528
Max Act: 4.0496. Min Act: -0.1700
Data Index: 7254860 (The Pile)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2528. Min Range: -4.2528
Max Act: 4.0340. Min Act: -0.1700
Data Index: 5186063 (The Pile)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2528. Min Range: -4.2528
Max Act: 4.0340. Min Act: -0.1700
Data Index: 9166476 (The Pile)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2528. Min Range: -4.2528
Max Act: 4.0340. Min Act: -0.1700
Data Index: 1627141 (The Pile)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2528. Min Range: -4.2528
Max Act: 4.0340. Min Act: -0.1700
Data Index: 7879722 (The Pile)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2528. Min Range: -4.2528
Max Act: 4.0340. Min Act: -0.1695
Data Index: 10182985 (The Pile)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19