Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 2753 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.1542. Min Range: -0.1542
Max Act: 0.1542. Min Act: -0.0002
Data Index: 69397 (The Pile)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1542. Min Range: -0.1542
Max Act: 0.1510. Min Act: -0.0001
Data Index: 238685 (The Pile)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1542. Min Range: -0.1542
Max Act: 0.0767. Min Act: -0.0003
Data Index: 400169 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1542. Min Range: -0.1542
Max Act: 0.0758. Min Act: -0.0002
Data Index: 1274996 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1542. Min Range: -0.1542
Max Act: 0.0711. Min Act: -0.0002
Data Index: 1579967 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1542. Min Range: -0.1542
Max Act: 0.0701. Min Act: -0.0002
Data Index: 1551825 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1542. Min Range: -0.1542
Max Act: 0.0688. Min Act: -0.0002
Data Index: 1084170 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1542. Min Range: -0.1542
Max Act: 0.0678. Min Act: -0.0003
Data Index: 9510 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1542. Min Range: -0.1542
Max Act: 0.0654. Min Act: -0.0003
Data Index: 571588 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1542. Min Range: -0.1542
Max Act: 0.0642. Min Act: -0.0003
Data Index: 1818723 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1542. Min Range: -0.1542
Max Act: 0.0631. Min Act: -0.0002
Data Index: 1192345 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1542. Min Range: -0.1542
Max Act: 0.0620. Min Act: -0.0002
Data Index: 1905396 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1542. Min Range: -0.1542
Max Act: 0.0586. Min Act: -0.0003
Data Index: 1457578 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1542. Min Range: -0.1542
Max Act: 0.0590. Min Act: -0.0003
Data Index: 44497 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1542. Min Range: -0.1542
Max Act: 0.0627. Min Act: -0.0003
Data Index: 1647316 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1542. Min Range: -0.1542
Max Act: 0.0591. Min Act: -0.0003
Data Index: 1652607 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1542. Min Range: -0.1542
Max Act: 0.0590. Min Act: -0.0002
Data Index: 845917 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1542. Min Range: -0.1542
Max Act: 0.0585. Min Act: -0.0003
Data Index: 1003695 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1542. Min Range: -0.1542
Max Act: 0.0589. Min Act: -0.0002
Data Index: 1834210 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1542. Min Range: -0.1542
Max Act: 0.0575. Min Act: -0.0002
Data Index: 1109469 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19