Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 766 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0980. Min Range: -0.0980
Max Act: 0.0980. Min Act: -0.0001
Data Index: 703074 (The Pile)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0980. Min Range: -0.0980
Max Act: 0.0756. Min Act: -0.0001
Data Index: 1078275 (The Pile)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0980. Min Range: -0.0980
Max Act: 0.0664. Min Act: -0.0001
Data Index: 737394 (The Pile)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0980. Min Range: -0.0980
Max Act: 0.0615. Min Act: -0.0001
Data Index: 1943667 (The Pile)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0980. Min Range: -0.0980
Max Act: 0.0643. Min Act: -0.0001
Data Index: 349640 (The Pile)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0980. Min Range: -0.0980
Max Act: 0.0589. Min Act: -0.0001
Data Index: 777452 (The Pile)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0980. Min Range: -0.0980
Max Act: 0.0610. Min Act: -0.0001
Data Index: 286601 (The Pile)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0980. Min Range: -0.0980
Max Act: 0.0612. Min Act: -0.0001
Data Index: 215400 (The Pile)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0980. Min Range: -0.0980
Max Act: 0.0603. Min Act: -0.0001
Data Index: 852107 (The Pile)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0980. Min Range: -0.0980
Max Act: 0.0599. Min Act: -0.0001
Data Index: 59569 (The Pile)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0980. Min Range: -0.0980
Max Act: 0.0577. Min Act: -0.0002
Data Index: 1003660 (The Pile)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0980. Min Range: -0.0980
Max Act: 0.0550. Min Act: -0.0001
Data Index: 1708867 (The Pile)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0980. Min Range: -0.0980
Max Act: 0.0589. Min Act: -0.0001
Data Index: 1848695 (The Pile)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0980. Min Range: -0.0980
Max Act: 0.0547. Min Act: -0.0001
Data Index: 1052728 (The Pile)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0980. Min Range: -0.0980
Max Act: 0.0556. Min Act: -0.0002
Data Index: 1929317 (The Pile)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0980. Min Range: -0.0980
Max Act: 0.0587. Min Act: -0.0001
Data Index: 184271 (The Pile)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0980. Min Range: -0.0980
Max Act: 0.0559. Min Act: -0.0001
Data Index: 117075 (The Pile)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0980. Min Range: -0.0980
Max Act: 0.0586. Min Act: -0.0001
Data Index: 932810 (The Pile)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0980. Min Range: -0.0980
Max Act: 0.0509. Min Act: -0.0001
Data Index: 1657147 (The Pile)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0980. Min Range: -0.0980
Max Act: 0.0541. Min Act: -0.0001
Data Index: 1338923 (The Pile)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19