Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2133 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.4514. Min Range: -2.4514
Max Act: 2.4514. Min Act: -0.0000
Data Index: 1055006 (The Pile)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4514. Min Range: -2.4514
Max Act: 2.1652. Min Act: -0.0000
Data Index: 615268 (The Pile)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4514. Min Range: -2.4514
Max Act: 2.0926. Min Act: -0.0000
Data Index: 851588 (The Pile)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4514. Min Range: -2.4514
Max Act: 1.7953. Min Act: -0.0000
Data Index: 1063302 (The Pile)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4514. Min Range: -2.4514
Max Act: 1.8370. Min Act: -0.0000
Data Index: 1879293 (The Pile)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4514. Min Range: -2.4514
Max Act: 1.7602. Min Act: -0.0000
Data Index: 1340609 (The Pile)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4514. Min Range: -2.4514
Max Act: 1.7651. Min Act: -0.0001
Data Index: 1570107 (The Pile)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4514. Min Range: -2.4514
Max Act: 1.6401. Min Act: -0.0000
Data Index: 82187 (The Pile)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4514. Min Range: -2.4514
Max Act: 1.8304. Min Act: -0.0000
Data Index: 121836 (The Pile)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4514. Min Range: -2.4514
Max Act: 1.6815. Min Act: -0.0000
Data Index: 228687 (The Pile)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4514. Min Range: -2.4514
Max Act: 1.5863. Min Act: -0.0000
Data Index: 1355953 (The Pile)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4514. Min Range: -2.4514
Max Act: 1.6051. Min Act: -0.0000
Data Index: 1858871 (The Pile)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4514. Min Range: -2.4514
Max Act: 1.5624. Min Act: -0.0000
Data Index: 372931 (The Pile)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4514. Min Range: -2.4514
Max Act: 1.4242. Min Act: -0.0000
Data Index: 828048 (The Pile)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4514. Min Range: -2.4514
Max Act: 1.5891. Min Act: -0.0000
Data Index: 1135502 (The Pile)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4514. Min Range: -2.4514
Max Act: 1.4607. Min Act: -0.0000
Data Index: 26560 (The Pile)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4514. Min Range: -2.4514
Max Act: 1.3695. Min Act: -0.0000
Data Index: 1119649 (The Pile)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4514. Min Range: -2.4514
Max Act: 1.3845. Min Act: -0.0000
Data Index: 1149939 (The Pile)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4514. Min Range: -2.4514
Max Act: 1.4163. Min Act: -0.0000
Data Index: 1940090 (The Pile)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4514. Min Range: -2.4514
Max Act: 1.2532. Min Act: -0.0000
Data Index: 1083971 (The Pile)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #19