Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1776 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.1015. Min Range: -0.1015
Max Act: 0.1015. Min Act: 0.0001
Data Index: 1325188 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1015. Min Range: -0.1015
Max Act: 0.1008. Min Act: -0.0000
Data Index: 268616 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1015. Min Range: -0.1015
Max Act: 0.0980. Min Act: 0.0000
Data Index: 1461377 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1015. Min Range: -0.1015
Max Act: 0.1015. Min Act: 0.0000
Data Index: 1590521 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1015. Min Range: -0.1015
Max Act: 0.0978. Min Act: 0.0000
Data Index: 757356 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1015. Min Range: -0.1015
Max Act: 0.0973. Min Act: 0.0000
Data Index: 64330 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1015. Min Range: -0.1015
Max Act: 0.0977. Min Act: -0.0000
Data Index: 1271968 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1015. Min Range: -0.1015
Max Act: 0.0939. Min Act: 0.0000
Data Index: 1763531 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1015. Min Range: -0.1015
Max Act: 0.0974. Min Act: -0.0000
Data Index: 1267045 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1015. Min Range: -0.1015
Max Act: 0.0969. Min Act: -0.0000
Data Index: 1388757 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1015. Min Range: -0.1015
Max Act: 0.0963. Min Act: -0.0000
Data Index: 1227026 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1015. Min Range: -0.1015
Max Act: 0.0963. Min Act: 0.0001
Data Index: 341311 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1015. Min Range: -0.1015
Max Act: 0.0955. Min Act: -0.0000
Data Index: 1353277 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1015. Min Range: -0.1015
Max Act: 0.0954. Min Act: -0.0000
Data Index: 229885 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1015. Min Range: -0.1015
Max Act: 0.0948. Min Act: 0.0000
Data Index: 1180318 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1015. Min Range: -0.1015
Max Act: 0.0951. Min Act: -0.0000
Data Index: 858753 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1015. Min Range: -0.1015
Max Act: 0.0950. Min Act: 0.0000
Data Index: 1136017 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1015. Min Range: -0.1015
Max Act: 0.0947. Min Act: 0.0000
Data Index: 1639239 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1015. Min Range: -0.1015
Max Act: 0.0947. Min Act: -0.0000
Data Index: 514930 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1015. Min Range: -0.1015
Max Act: 0.0938. Min Act: -0.0000
Data Index: 835224 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19