Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1995 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.3465. Min Range: -2.3465
Max Act: 2.3465. Min Act: -0.0000
Data Index: 640203 (The Pile)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3465. Min Range: -2.3465
Max Act: 2.3191. Min Act: -0.0000
Data Index: 1663283 (The Pile)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3465. Min Range: -2.3465
Max Act: 2.2683. Min Act: -0.0000
Data Index: 1497384 (The Pile)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3465. Min Range: -2.3465
Max Act: 2.1906. Min Act: -0.0000
Data Index: 1963679 (The Pile)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3465. Min Range: -2.3465
Max Act: 2.0354. Min Act: -0.0000
Data Index: 1296623 (The Pile)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3465. Min Range: -2.3465
Max Act: 2.1184. Min Act: -0.0000
Data Index: 1771077 (The Pile)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3465. Min Range: -2.3465
Max Act: 2.0407. Min Act: -0.0000
Data Index: 8537 (The Pile)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3465. Min Range: -2.3465
Max Act: 2.0239. Min Act: -0.0000
Data Index: 1219300 (The Pile)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3465. Min Range: -2.3465
Max Act: 1.9748. Min Act: -0.0000
Data Index: 1828672 (The Pile)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3465. Min Range: -2.3465
Max Act: 1.9574. Min Act: -0.0000
Data Index: 461406 (The Pile)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3465. Min Range: -2.3465
Max Act: 1.9512. Min Act: -0.0000
Data Index: 1437446 (The Pile)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3465. Min Range: -2.3465
Max Act: 1.9546. Min Act: -0.0000
Data Index: 1326960 (The Pile)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3465. Min Range: -2.3465
Max Act: 1.8749. Min Act: -0.0000
Data Index: 1507326 (The Pile)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3465. Min Range: -2.3465
Max Act: 1.7432. Min Act: -0.0000
Data Index: 1082613 (The Pile)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3465. Min Range: -2.3465
Max Act: 1.7046. Min Act: -0.0000
Data Index: 147377 (The Pile)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3465. Min Range: -2.3465
Max Act: 1.7742. Min Act: -0.0000
Data Index: 603867 (The Pile)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3465. Min Range: -2.3465
Max Act: 1.7509. Min Act: -0.0000
Data Index: 9999 (The Pile)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3465. Min Range: -2.3465
Max Act: 1.6485. Min Act: -0.0000
Data Index: 16533 (The Pile)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3465. Min Range: -2.3465
Max Act: 1.7373. Min Act: -0.0000
Data Index: 754161 (The Pile)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3465. Min Range: -2.3465
Max Act: 1.7250. Min Act: -0.0000
Data Index: 1970403 (The Pile)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19