Model: None
Dataset: The Pile
Neuron 902 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 9.3647. Min Range: -9.3647
Max Act: 9.3647. Min Act: -0.1424
Data Index: 3243155 (The Pile)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3647. Min Range: -9.3647
Max Act: 9.3022. Min Act: -0.1484
Data Index: 1708735 (The Pile)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3647. Min Range: -9.3647
Max Act: 9.0522. Min Act: -0.1696
Data Index: 9601028 (The Pile)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3647. Min Range: -9.3647
Max Act: 9.1147. Min Act: -0.1700
Data Index: 3215160 (The Pile)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3647. Min Range: -9.3647
Max Act: 9.0522. Min Act: -0.1458
Data Index: 10795268 (The Pile)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3647. Min Range: -9.3647
Max Act: 9.0522. Min Act: -0.1417
Data Index: 9232751 (The Pile)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3647. Min Range: -9.3647
Max Act: 8.9897. Min Act: -0.1465
Data Index: 8010890 (The Pile)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3647. Min Range: -9.3647
Max Act: 9.0522. Min Act: -0.1458
Data Index: 5790345 (The Pile)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3647. Min Range: -9.3647
Max Act: 8.9897. Min Act: -0.1556
Data Index: 10264334 (The Pile)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3647. Min Range: -9.3647
Max Act: 8.9897. Min Act: -0.1683
Data Index: 8587026 (The Pile)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3647. Min Range: -9.3647
Max Act: 8.9897. Min Act: -0.1478
Data Index: 9199687 (The Pile)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3647. Min Range: -9.3647
Max Act: 9.1147. Min Act: -0.1458
Data Index: 1856685 (The Pile)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3647. Min Range: -9.3647
Max Act: 8.9272. Min Act: -0.1340
Data Index: 6736922 (The Pile)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3647. Min Range: -9.3647
Max Act: 9.0522. Min Act: -0.1452
Data Index: 4418625 (The Pile)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3647. Min Range: -9.3647
Max Act: 8.8647. Min Act: -0.1691
Data Index: 8874979 (The Pile)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3647. Min Range: -9.3647
Max Act: 8.8647. Min Act: -0.1700
Data Index: 6177011 (The Pile)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3647. Min Range: -9.3647
Max Act: 8.9272. Min Act: -0.1365
Data Index: 3852305 (The Pile)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3647. Min Range: -9.3647
Max Act: 8.8647. Min Act: -0.1372
Data Index: 3905453 (The Pile)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3647. Min Range: -9.3647
Max Act: 8.9272. Min Act: -0.1668
Data Index: 375984 (The Pile)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3647. Min Range: -9.3647
Max Act: 8.8647. Min Act: -0.1676
Data Index: 1786795 (The Pile)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #19