Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 683 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.2809. Min Range: -1.2809
Max Act: 1.2809. Min Act: -0.0000
Data Index: 642429 (The Pile)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2809. Min Range: -1.2809
Max Act: 1.1192. Min Act: -0.0000
Data Index: 985603 (The Pile)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2809. Min Range: -1.2809
Max Act: 1.0199. Min Act: -0.0000
Data Index: 1769404 (The Pile)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2809. Min Range: -1.2809
Max Act: 0.9097. Min Act: -0.0000
Data Index: 1632256 (The Pile)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2809. Min Range: -1.2809
Max Act: 0.9190. Min Act: -0.0000
Data Index: 39168 (The Pile)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2809. Min Range: -1.2809
Max Act: 0.9219. Min Act: -0.0000
Data Index: 92301 (The Pile)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2809. Min Range: -1.2809
Max Act: 0.9581. Min Act: -0.0000
Data Index: 1109553 (The Pile)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2809. Min Range: -1.2809
Max Act: 0.9529. Min Act: -0.0000
Data Index: 51987 (The Pile)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2809. Min Range: -1.2809
Max Act: 0.8637. Min Act: -0.0000
Data Index: 283056 (The Pile)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2809. Min Range: -1.2809
Max Act: 0.8524. Min Act: -0.0000
Data Index: 1966322 (The Pile)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2809. Min Range: -1.2809
Max Act: 0.8592. Min Act: -0.0000
Data Index: 1366391 (The Pile)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2809. Min Range: -1.2809
Max Act: 0.8513. Min Act: -0.0000
Data Index: 1918465 (The Pile)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2809. Min Range: -1.2809
Max Act: 0.9018. Min Act: -0.0000
Data Index: 1781801 (The Pile)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2809. Min Range: -1.2809
Max Act: 0.8777. Min Act: -0.0000
Data Index: 972905 (The Pile)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2809. Min Range: -1.2809
Max Act: 0.8572. Min Act: -0.0000
Data Index: 1603628 (The Pile)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2809. Min Range: -1.2809
Max Act: 0.8686. Min Act: -0.0000
Data Index: 982462 (The Pile)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2809. Min Range: -1.2809
Max Act: 0.8390. Min Act: -0.0000
Data Index: 1110285 (The Pile)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2809. Min Range: -1.2809
Max Act: 0.8245. Min Act: -0.0000
Data Index: 1697483 (The Pile)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2809. Min Range: -1.2809
Max Act: 0.8657. Min Act: -0.0000
Data Index: 462358 (The Pile)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2809. Min Range: -1.2809
Max Act: 0.8149. Min Act: -0.0000
Data Index: 198543 (The Pile)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19