Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 4063 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.6855. Min Range: -0.6855
Max Act: 0.6410. Min Act: -0.0001
Data Index: 1860971 (The Pile)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6855. Min Range: -0.6855
Max Act: 0.6855. Min Act: -0.0001
Data Index: 1167592 (The Pile)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6855. Min Range: -0.6855
Max Act: 0.6643. Min Act: -0.0001
Data Index: 388201 (The Pile)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6855. Min Range: -0.6855
Max Act: 0.5964. Min Act: -0.0002
Data Index: 1132319 (The Pile)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6855. Min Range: -0.6855
Max Act: 0.5913. Min Act: -0.0001
Data Index: 578766 (The Pile)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6855. Min Range: -0.6855
Max Act: 0.6101. Min Act: -0.0001
Data Index: 1778421 (The Pile)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6855. Min Range: -0.6855
Max Act: 0.5752. Min Act: -0.0001
Data Index: 899189 (The Pile)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6855. Min Range: -0.6855
Max Act: 0.5014. Min Act: -0.0001
Data Index: 1970346 (The Pile)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6855. Min Range: -0.6855
Max Act: 0.5341. Min Act: -0.0001
Data Index: 803675 (The Pile)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6855. Min Range: -0.6855
Max Act: 0.5631. Min Act: -0.0001
Data Index: 1509492 (The Pile)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6855. Min Range: -0.6855
Max Act: 0.5623. Min Act: -0.0001
Data Index: 483345 (The Pile)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6855. Min Range: -0.6855
Max Act: 0.5437. Min Act: -0.0001
Data Index: 1927967 (The Pile)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6855. Min Range: -0.6855
Max Act: 0.5951. Min Act: -0.0001
Data Index: 10667 (The Pile)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6855. Min Range: -0.6855
Max Act: 0.5804. Min Act: -0.0001
Data Index: 1392940 (The Pile)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6855. Min Range: -0.6855
Max Act: 0.5355. Min Act: -0.0001
Data Index: 1260254 (The Pile)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6855. Min Range: -0.6855
Max Act: 0.5708. Min Act: -0.0001
Data Index: 673649 (The Pile)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6855. Min Range: -0.6855
Max Act: 0.6033. Min Act: -0.0001
Data Index: 627031 (The Pile)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6855. Min Range: -0.6855
Max Act: 0.4941. Min Act: -0.0001
Data Index: 1803196 (The Pile)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6855. Min Range: -0.6855
Max Act: 0.5765. Min Act: -0.0001
Data Index: 1974113 (The Pile)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6855. Min Range: -0.6855
Max Act: 0.5625. Min Act: -0.0001
Data Index: 1590209 (The Pile)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19