Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2729 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.0820. Min Range: -2.0820
Max Act: 1.9250. Min Act: -0.0000
Data Index: 1241772 (The Pile)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0820. Min Range: -2.0820
Max Act: 1.8244. Min Act: -0.0000
Data Index: 295564 (The Pile)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0820. Min Range: -2.0820
Max Act: 2.0820. Min Act: -0.0000
Data Index: 1837934 (The Pile)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0820. Min Range: -2.0820
Max Act: 1.8067. Min Act: -0.0000
Data Index: 93241 (The Pile)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0820. Min Range: -2.0820
Max Act: 1.8060. Min Act: -0.0000
Data Index: 1111605 (The Pile)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0820. Min Range: -2.0820
Max Act: 1.7418. Min Act: -0.0000
Data Index: 1520151 (The Pile)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0820. Min Range: -2.0820
Max Act: 1.2623. Min Act: -0.0000
Data Index: 1445309 (The Pile)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0820. Min Range: -2.0820
Max Act: 1.5057. Min Act: -0.0000
Data Index: 257224 (The Pile)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0820. Min Range: -2.0820
Max Act: 1.6030. Min Act: -0.0000
Data Index: 395516 (The Pile)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0820. Min Range: -2.0820
Max Act: 1.4707. Min Act: -0.0000
Data Index: 865931 (The Pile)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0820. Min Range: -2.0820
Max Act: 1.4809. Min Act: -0.0000
Data Index: 99018 (The Pile)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0820. Min Range: -2.0820
Max Act: 1.2992. Min Act: -0.0000
Data Index: 308099 (The Pile)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0820. Min Range: -2.0820
Max Act: 1.3356. Min Act: -0.0000
Data Index: 347707 (The Pile)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0820. Min Range: -2.0820
Max Act: 1.4056. Min Act: -0.0000
Data Index: 444877 (The Pile)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0820. Min Range: -2.0820
Max Act: 1.3214. Min Act: -0.0000
Data Index: 551068 (The Pile)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0820. Min Range: -2.0820
Max Act: 1.3069. Min Act: -0.0000
Data Index: 1885433 (The Pile)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0820. Min Range: -2.0820
Max Act: 1.4151. Min Act: -0.0000
Data Index: 1405990 (The Pile)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0820. Min Range: -2.0820
Max Act: 1.3285. Min Act: -0.0000
Data Index: 1189938 (The Pile)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0820. Min Range: -2.0820
Max Act: 1.2549. Min Act: -0.0000
Data Index: 8788 (The Pile)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0820. Min Range: -2.0820
Max Act: 1.2079. Min Act: -0.0000
Data Index: 466720 (The Pile)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19