Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 558 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.2402. Min Range: -1.2402
Max Act: 1.2402. Min Act: -0.0000
Data Index: 1510442 (The Pile)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2402. Min Range: -1.2402
Max Act: 1.0508. Min Act: -0.0000
Data Index: 1883708 (The Pile)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2402. Min Range: -1.2402
Max Act: 1.0159. Min Act: -0.0000
Data Index: 443821 (The Pile)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2402. Min Range: -1.2402
Max Act: 0.9415. Min Act: -0.0000
Data Index: 185872 (The Pile)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2402. Min Range: -1.2402
Max Act: 0.9766. Min Act: -0.0000
Data Index: 1868972 (The Pile)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2402. Min Range: -1.2402
Max Act: 0.9113. Min Act: -0.0000
Data Index: 1086201 (The Pile)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2402. Min Range: -1.2402
Max Act: 0.9185. Min Act: -0.0000
Data Index: 40221 (The Pile)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2402. Min Range: -1.2402
Max Act: 0.8866. Min Act: -0.0000
Data Index: 243817 (The Pile)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2402. Min Range: -1.2402
Max Act: 0.8344. Min Act: -0.0000
Data Index: 999371 (The Pile)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2402. Min Range: -1.2402
Max Act: 0.8249. Min Act: -0.0000
Data Index: 1390404 (The Pile)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2402. Min Range: -1.2402
Max Act: 0.8358. Min Act: -0.0000
Data Index: 610471 (The Pile)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2402. Min Range: -1.2402
Max Act: 0.8459. Min Act: -0.0000
Data Index: 212667 (The Pile)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2402. Min Range: -1.2402
Max Act: 0.7519. Min Act: -0.0000
Data Index: 245934 (The Pile)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2402. Min Range: -1.2402
Max Act: 0.8079. Min Act: -0.0000
Data Index: 328305 (The Pile)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2402. Min Range: -1.2402
Max Act: 0.7662. Min Act: -0.0000
Data Index: 362900 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2402. Min Range: -1.2402
Max Act: 0.7133. Min Act: -0.0000
Data Index: 1619572 (The Pile)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2402. Min Range: -1.2402
Max Act: 0.7656. Min Act: -0.0000
Data Index: 345674 (The Pile)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2402. Min Range: -1.2402
Max Act: 0.8029. Min Act: -0.0000
Data Index: 1004886 (The Pile)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2402. Min Range: -1.2402
Max Act: 0.8433. Min Act: -0.0000
Data Index: 1673586 (The Pile)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2402. Min Range: -1.2402
Max Act: 0.7696. Min Act: -0.0000
Data Index: 1993398 (The Pile)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19