Model: None
Dataset: The Pile
Neuron 970 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 3.1323. Min Range: -3.1323
Max Act: 2.7680. Min Act: -0.1700
Data Index: 3637963 (The Pile)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1323. Min Range: -3.1323
Max Act: 3.0060. Min Act: -0.1700
Data Index: 9274254 (The Pile)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1323. Min Range: -3.1323
Max Act: 2.7520. Min Act: -0.1700
Data Index: 10777445 (The Pile)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1323. Min Range: -3.1323
Max Act: 2.7360. Min Act: -0.1700
Data Index: 6978528 (The Pile)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1323. Min Range: -3.1323
Max Act: 2.7680. Min Act: -0.1700
Data Index: 1058833 (The Pile)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1323. Min Range: -3.1323
Max Act: 2.7680. Min Act: -0.1700
Data Index: 7328859 (The Pile)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1323. Min Range: -3.1323
Max Act: 3.0692. Min Act: -0.1700
Data Index: 6764958 (The Pile)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1323. Min Range: -3.1323
Max Act: 2.9269. Min Act: -0.1699
Data Index: 6360643 (The Pile)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1323. Min Range: -3.1323
Max Act: 3.1323. Min Act: -0.1700
Data Index: 7703398 (The Pile)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1323. Min Range: -3.1323
Max Act: 2.9586. Min Act: -0.1700
Data Index: 542275 (The Pile)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1323. Min Range: -3.1323
Max Act: 2.8317. Min Act: -0.1700
Data Index: 7552235 (The Pile)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1323. Min Range: -3.1323
Max Act: 3.0376. Min Act: -0.1700
Data Index: 9524748 (The Pile)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1323. Min Range: -3.1323
Max Act: 2.9269. Min Act: -0.1700
Data Index: 4586568 (The Pile)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1323. Min Range: -3.1323
Max Act: 2.7520. Min Act: -0.1700
Data Index: 4662224 (The Pile)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1323. Min Range: -3.1323
Max Act: 2.8635. Min Act: -0.1700
Data Index: 9712483 (The Pile)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1323. Min Range: -3.1323
Max Act: 3.0534. Min Act: -0.1700
Data Index: 3102119 (The Pile)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1323. Min Range: -3.1323
Max Act: 2.8635. Min Act: -0.1699
Data Index: 4932901 (The Pile)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1323. Min Range: -3.1323
Max Act: 2.8476. Min Act: -0.1700
Data Index: 1115515 (The Pile)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1323. Min Range: -3.1323
Max Act: 2.8476. Min Act: -0.1700
Data Index: 6904394 (The Pile)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1323. Min Range: -3.1323
Max Act: 2.8317. Min Act: -0.1700
Data Index: 1064806 (The Pile)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19