Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 83 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.0641. Min Range: -1.0641
Max Act: 0.8030. Min Act: -0.0001
Data Index: 638052 (The Pile)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0641. Min Range: -1.0641
Max Act: 1.0543. Min Act: -0.0001
Data Index: 853884 (The Pile)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0641. Min Range: -1.0641
Max Act: 1.0641. Min Act: -0.0001
Data Index: 674936 (The Pile)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0641. Min Range: -1.0641
Max Act: 1.0025. Min Act: -0.0001
Data Index: 1309114 (The Pile)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0641. Min Range: -1.0641
Max Act: 1.0538. Min Act: -0.0001
Data Index: 1600757 (The Pile)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0641. Min Range: -1.0641
Max Act: 1.0138. Min Act: -0.0001
Data Index: 189566 (The Pile)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0641. Min Range: -1.0641
Max Act: 1.0475. Min Act: -0.0001
Data Index: 1905827 (The Pile)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0641. Min Range: -1.0641
Max Act: 0.8878. Min Act: -0.0001
Data Index: 1695090 (The Pile)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0641. Min Range: -1.0641
Max Act: 0.9081. Min Act: -0.0001
Data Index: 1069846 (The Pile)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0641. Min Range: -1.0641
Max Act: 0.9279. Min Act: -0.0001
Data Index: 728285 (The Pile)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0641. Min Range: -1.0641
Max Act: 0.9878. Min Act: -0.0001
Data Index: 1762355 (The Pile)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0641. Min Range: -1.0641
Max Act: 0.9433. Min Act: -0.0001
Data Index: 1220248 (The Pile)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0641. Min Range: -1.0641
Max Act: 1.0372. Min Act: -0.0001
Data Index: 884674 (The Pile)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0641. Min Range: -1.0641
Max Act: 0.9097. Min Act: -0.0001
Data Index: 1476356 (The Pile)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0641. Min Range: -1.0641
Max Act: 0.6883. Min Act: -0.0001
Data Index: 102783 (The Pile)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0641. Min Range: -1.0641
Max Act: 0.9156. Min Act: -0.0001
Data Index: 1024976 (The Pile)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0641. Min Range: -1.0641
Max Act: 0.8954. Min Act: -0.0001
Data Index: 302719 (The Pile)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0641. Min Range: -1.0641
Max Act: 0.7536. Min Act: -0.0001
Data Index: 1514380 (The Pile)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0641. Min Range: -1.0641
Max Act: 0.8573. Min Act: -0.0001
Data Index: 1074064 (The Pile)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0641. Min Range: -1.0641
Max Act: 0.8230. Min Act: -0.0001
Data Index: 195083 (The Pile)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19