Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 3064 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.4041. Min Range: -2.4041
Max Act: 2.4041. Min Act: -0.0000
Data Index: 1894005 (The Pile)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4041. Min Range: -2.4041
Max Act: 1.9611. Min Act: -0.0000
Data Index: 607017 (The Pile)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4041. Min Range: -2.4041
Max Act: 1.8913. Min Act: -0.0000
Data Index: 28179 (The Pile)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4041. Min Range: -2.4041
Max Act: 1.9445. Min Act: -0.0000
Data Index: 687527 (The Pile)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4041. Min Range: -2.4041
Max Act: 1.8316. Min Act: -0.0000
Data Index: 920449 (The Pile)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4041. Min Range: -2.4041
Max Act: 2.1392. Min Act: -0.0000
Data Index: 899550 (The Pile)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4041. Min Range: -2.4041
Max Act: 1.9013. Min Act: -0.0000
Data Index: 725795 (The Pile)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4041. Min Range: -2.4041
Max Act: 1.8734. Min Act: -0.0000
Data Index: 139553 (The Pile)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4041. Min Range: -2.4041
Max Act: 1.8656. Min Act: -0.0000
Data Index: 1639810 (The Pile)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4041. Min Range: -2.4041
Max Act: 1.7467. Min Act: -0.0000
Data Index: 1143817 (The Pile)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4041. Min Range: -2.4041
Max Act: 1.9599. Min Act: -0.0000
Data Index: 1977986 (The Pile)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4041. Min Range: -2.4041
Max Act: 1.7311. Min Act: -0.0000
Data Index: 1512765 (The Pile)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4041. Min Range: -2.4041
Max Act: 1.8106. Min Act: -0.0000
Data Index: 1221584 (The Pile)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4041. Min Range: -2.4041
Max Act: 1.7532. Min Act: -0.0000
Data Index: 1817531 (The Pile)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4041. Min Range: -2.4041
Max Act: 1.7589. Min Act: -0.0000
Data Index: 1279626 (The Pile)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4041. Min Range: -2.4041
Max Act: 1.7546. Min Act: -0.0000
Data Index: 53434 (The Pile)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4041. Min Range: -2.4041
Max Act: 1.7932. Min Act: -0.0000
Data Index: 608745 (The Pile)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4041. Min Range: -2.4041
Max Act: 1.6687. Min Act: -0.0000
Data Index: 81669 (The Pile)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4041. Min Range: -2.4041
Max Act: 1.6749. Min Act: -0.0000
Data Index: 1346271 (The Pile)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4041. Min Range: -2.4041
Max Act: 1.6764. Min Act: -0.0000
Data Index: 392171 (The Pile)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #19