Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1886 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.9360. Min Range: -1.9360
Max Act: 1.9360. Min Act: -0.0000
Data Index: 1683613 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9360. Min Range: -1.9360
Max Act: 1.8351. Min Act: -0.0000
Data Index: 1101257 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9360. Min Range: -1.9360
Max Act: 1.6288. Min Act: -0.0000
Data Index: 402652 (The Pile)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9360. Min Range: -1.9360
Max Act: 1.7257. Min Act: -0.0000
Data Index: 1018909 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9360. Min Range: -1.9360
Max Act: 1.5903. Min Act: -0.0000
Data Index: 1280704 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9360. Min Range: -1.9360
Max Act: 1.5646. Min Act: -0.0000
Data Index: 1835010 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9360. Min Range: -1.9360
Max Act: 1.5794. Min Act: -0.0000
Data Index: 1472349 (The Pile)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9360. Min Range: -1.9360
Max Act: 1.5090. Min Act: -0.0000
Data Index: 1114909 (The Pile)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9360. Min Range: -1.9360
Max Act: 1.5435. Min Act: -0.0000
Data Index: 964537 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9360. Min Range: -1.9360
Max Act: 1.4134. Min Act: -0.0000
Data Index: 1865827 (The Pile)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9360. Min Range: -1.9360
Max Act: 1.4098. Min Act: -0.0000
Data Index: 792397 (The Pile)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9360. Min Range: -1.9360
Max Act: 1.4268. Min Act: -0.0000
Data Index: 1822466 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9360. Min Range: -1.9360
Max Act: 1.4840. Min Act: -0.0000
Data Index: 693814 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9360. Min Range: -1.9360
Max Act: 1.4938. Min Act: -0.0000
Data Index: 1550891 (The Pile)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9360. Min Range: -1.9360
Max Act: 1.4495. Min Act: -0.0000
Data Index: 92243 (The Pile)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9360. Min Range: -1.9360
Max Act: 1.3626. Min Act: -0.0000
Data Index: 1452197 (The Pile)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9360. Min Range: -1.9360
Max Act: 1.2742. Min Act: -0.0000
Data Index: 1114303 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9360. Min Range: -1.9360
Max Act: 1.3125. Min Act: -0.0000
Data Index: 1875559 (The Pile)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9360. Min Range: -1.9360
Max Act: 1.2651. Min Act: -0.0000
Data Index: 1269513 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9360. Min Range: -1.9360
Max Act: 1.2456. Min Act: -0.0000
Data Index: 1713272 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19