Model: None
Dataset: The Pile
Neuron 401 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 4.0568. Min Range: -4.0568
Max Act: 4.0568. Min Act: -0.1700
Data Index: 5510914 (The Pile)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0568. Min Range: -4.0568
Max Act: 3.9943. Min Act: -0.1700
Data Index: 9733040 (The Pile)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0568. Min Range: -4.0568
Max Act: 3.9786. Min Act: -0.1700
Data Index: 1480917 (The Pile)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0568. Min Range: -4.0568
Max Act: 3.9786. Min Act: -0.1700
Data Index: 1158499 (The Pile)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0568. Min Range: -4.0568
Max Act: 3.9474. Min Act: -0.1700
Data Index: 9714689 (The Pile)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0568. Min Range: -4.0568
Max Act: 3.9474. Min Act: -0.1700
Data Index: 5518491 (The Pile)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0568. Min Range: -4.0568
Max Act: 3.9474. Min Act: -0.1700
Data Index: 2401029 (The Pile)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0568. Min Range: -4.0568
Max Act: 3.9005. Min Act: -0.1700
Data Index: 3757391 (The Pile)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0568. Min Range: -4.0568
Max Act: 3.8848. Min Act: -0.1700
Data Index: 5987008 (The Pile)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0568. Min Range: -4.0568
Max Act: 3.8692. Min Act: -0.1700
Data Index: 7973682 (The Pile)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0568. Min Range: -4.0568
Max Act: 3.8692. Min Act: -0.1700
Data Index: 8944330 (The Pile)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0568. Min Range: -4.0568
Max Act: 3.8692. Min Act: -0.1700
Data Index: 10178543 (The Pile)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0568. Min Range: -4.0568
Max Act: 3.8692. Min Act: -0.1700
Data Index: 10101136 (The Pile)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0568. Min Range: -4.0568
Max Act: 3.8692. Min Act: -0.1700
Data Index: 4921908 (The Pile)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0568. Min Range: -4.0568
Max Act: 3.8692. Min Act: -0.1700
Data Index: 6714786 (The Pile)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0568. Min Range: -4.0568
Max Act: 3.8536. Min Act: -0.1700
Data Index: 6999227 (The Pile)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0568. Min Range: -4.0568
Max Act: 3.8536. Min Act: -0.1700
Data Index: 3696216 (The Pile)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0568. Min Range: -4.0568
Max Act: 3.8536. Min Act: -0.1700
Data Index: 7345715 (The Pile)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0568. Min Range: -4.0568
Max Act: 3.8379. Min Act: -0.1700
Data Index: 5171684 (The Pile)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0568. Min Range: -4.0568
Max Act: 3.8379. Min Act: -0.1700
Data Index: 2065306 (The Pile)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19