Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 3437 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.0126. Min Range: -2.0126
Max Act: 2.0126. Min Act: -0.0000
Data Index: 1890147 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0126. Min Range: -2.0126
Max Act: 1.7116. Min Act: -0.0000
Data Index: 1109644 (The Pile)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0126. Min Range: -2.0126
Max Act: 1.8120. Min Act: -0.0000
Data Index: 334736 (The Pile)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0126. Min Range: -2.0126
Max Act: 1.5216. Min Act: -0.0000
Data Index: 449188 (The Pile)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0126. Min Range: -2.0126
Max Act: 1.6055. Min Act: -0.0000
Data Index: 877695 (The Pile)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0126. Min Range: -2.0126
Max Act: 1.5817. Min Act: -0.0000
Data Index: 1593198 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0126. Min Range: -2.0126
Max Act: 1.4887. Min Act: -0.0000
Data Index: 979029 (The Pile)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0126. Min Range: -2.0126
Max Act: 1.4779. Min Act: -0.0000
Data Index: 1167823 (The Pile)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0126. Min Range: -2.0126
Max Act: 1.5707. Min Act: -0.0000
Data Index: 1090878 (The Pile)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0126. Min Range: -2.0126
Max Act: 1.5639. Min Act: -0.0000
Data Index: 633125 (The Pile)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0126. Min Range: -2.0126
Max Act: 1.7119. Min Act: -0.0000
Data Index: 1250526 (The Pile)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0126. Min Range: -2.0126
Max Act: 1.5273. Min Act: -0.0000
Data Index: 387992 (The Pile)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0126. Min Range: -2.0126
Max Act: 1.3459. Min Act: -0.0000
Data Index: 369929 (The Pile)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0126. Min Range: -2.0126
Max Act: 1.5227. Min Act: -0.0000
Data Index: 1932193 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0126. Min Range: -2.0126
Max Act: 1.6019. Min Act: -0.0000
Data Index: 1451343 (The Pile)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0126. Min Range: -2.0126
Max Act: 1.5011. Min Act: -0.0000
Data Index: 334771 (The Pile)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0126. Min Range: -2.0126
Max Act: 1.3773. Min Act: -0.0000
Data Index: 711689 (The Pile)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0126. Min Range: -2.0126
Max Act: 1.3149. Min Act: -0.0000
Data Index: 303470 (The Pile)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0126. Min Range: -2.0126
Max Act: 1.4917. Min Act: -0.0000
Data Index: 956347 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0126. Min Range: -2.0126
Max Act: 1.3976. Min Act: -0.0000
Data Index: 331181 (The Pile)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19