Model: None
Dataset: The Pile
Neuron 571 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 2.9525. Min Range: -2.9525
Max Act: 2.9525. Min Act: -0.1700
Data Index: 5070650 (The Pile)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9525. Min Range: -2.9525
Max Act: 2.9525. Min Act: -0.1700
Data Index: 657214 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9525. Min Range: -2.9525
Max Act: 2.9525. Min Act: -0.1700
Data Index: 5273877 (The Pile)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9525. Min Range: -2.9525
Max Act: 2.9208. Min Act: -0.1700
Data Index: 3918028 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9525. Min Range: -2.9525
Max Act: 2.9208. Min Act: -0.1700
Data Index: 5582300 (The Pile)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9525. Min Range: -2.9525
Max Act: 2.9050. Min Act: -0.1700
Data Index: 5765571 (The Pile)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9525. Min Range: -2.9525
Max Act: 2.8891. Min Act: -0.1700
Data Index: 6177339 (The Pile)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9525. Min Range: -2.9525
Max Act: 2.8574. Min Act: -0.1700
Data Index: 766009 (The Pile)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9525. Min Range: -2.9525
Max Act: 2.8574. Min Act: -0.1700
Data Index: 4380128 (The Pile)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9525. Min Range: -2.9525
Max Act: 2.8574. Min Act: -0.1695
Data Index: 560231 (The Pile)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9525. Min Range: -2.9525
Max Act: 2.8574. Min Act: -0.1700
Data Index: 5223634 (The Pile)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9525. Min Range: -2.9525
Max Act: 2.8415. Min Act: -0.1700
Data Index: 10526362 (The Pile)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9525. Min Range: -2.9525
Max Act: 2.8415. Min Act: -0.1700
Data Index: 4966824 (The Pile)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9525. Min Range: -2.9525
Max Act: 2.8415. Min Act: -0.1700
Data Index: 3180064 (The Pile)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9525. Min Range: -2.9525
Max Act: 2.8256. Min Act: -0.1700
Data Index: 2176253 (The Pile)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9525. Min Range: -2.9525
Max Act: 2.8256. Min Act: -0.1700
Data Index: 9705530 (The Pile)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9525. Min Range: -2.9525
Max Act: 2.8256. Min Act: -0.1700
Data Index: 839546 (The Pile)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9525. Min Range: -2.9525
Max Act: 2.8256. Min Act: -0.1700
Data Index: 810406 (The Pile)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9525. Min Range: -2.9525
Max Act: 2.8256. Min Act: -0.1700
Data Index: 9300648 (The Pile)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9525. Min Range: -2.9525
Max Act: 2.8256. Min Act: -0.1700
Data Index: 4153798 (The Pile)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19