Model: None
Dataset: The Pile
Neuron 761 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 3.0373. Min Range: -3.0373
Max Act: 3.0373. Min Act: -0.1700
Data Index: 8438302 (The Pile)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0373. Min Range: -3.0373
Max Act: 2.8948. Min Act: -0.1700
Data Index: 10020949 (The Pile)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0373. Min Range: -3.0373
Max Act: 2.8790. Min Act: -0.1700
Data Index: 2379543 (The Pile)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0373. Min Range: -3.0373
Max Act: 2.8790. Min Act: -0.1700
Data Index: 3687552 (The Pile)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0373. Min Range: -3.0373
Max Act: 2.8948. Min Act: -0.1700
Data Index: 1518781 (The Pile)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0373. Min Range: -3.0373
Max Act: 2.8948. Min Act: -0.1700
Data Index: 6853366 (The Pile)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0373. Min Range: -3.0373
Max Act: 2.8631. Min Act: -0.1700
Data Index: 9822169 (The Pile)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0373. Min Range: -3.0373
Max Act: 2.8631. Min Act: -0.1700
Data Index: 10028184 (The Pile)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0373. Min Range: -3.0373
Max Act: 2.8472. Min Act: -0.1700
Data Index: 6003671 (The Pile)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0373. Min Range: -3.0373
Max Act: 2.8631. Min Act: -0.1700
Data Index: 6442746 (The Pile)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0373. Min Range: -3.0373
Max Act: 2.8313. Min Act: -0.1700
Data Index: 5816364 (The Pile)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0373. Min Range: -3.0373
Max Act: 2.8472. Min Act: -0.1700
Data Index: 9819243 (The Pile)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0373. Min Range: -3.0373
Max Act: 2.8313. Min Act: -0.1700
Data Index: 1961645 (The Pile)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0373. Min Range: -3.0373
Max Act: 2.8154. Min Act: -0.1700
Data Index: 10536419 (The Pile)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0373. Min Range: -3.0373
Max Act: 2.7995. Min Act: -0.1700
Data Index: 433302 (The Pile)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0373. Min Range: -3.0373
Max Act: 2.8313. Min Act: -0.1700
Data Index: 5566740 (The Pile)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0373. Min Range: -3.0373
Max Act: 2.7835. Min Act: -0.1700
Data Index: 686472 (The Pile)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0373. Min Range: -3.0373
Max Act: 2.8154. Min Act: -0.1700
Data Index: 10165913 (The Pile)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0373. Min Range: -3.0373
Max Act: 2.7995. Min Act: -0.1700
Data Index: 8790919 (The Pile)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0373. Min Range: -3.0373
Max Act: 2.7676. Min Act: -0.1700
Data Index: 3486958 (The Pile)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19