Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2938 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.7051. Min Range: -2.7051
Max Act: 2.7051. Min Act: -0.0000
Data Index: 1362171 (The Pile)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7051. Min Range: -2.7051
Max Act: 2.6556. Min Act: -0.0000
Data Index: 950238 (The Pile)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7051. Min Range: -2.7051
Max Act: 2.6515. Min Act: -0.0000
Data Index: 864693 (The Pile)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7051. Min Range: -2.7051
Max Act: 2.6490. Min Act: -0.0000
Data Index: 1597117 (The Pile)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7051. Min Range: -2.7051
Max Act: 2.5147. Min Act: -0.0000
Data Index: 1212586 (The Pile)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7051. Min Range: -2.7051
Max Act: 2.3402. Min Act: -0.0000
Data Index: 281095 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7051. Min Range: -2.7051
Max Act: 2.5322. Min Act: -0.0000
Data Index: 559456 (The Pile)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7051. Min Range: -2.7051
Max Act: 2.4022. Min Act: -0.0000
Data Index: 773519 (The Pile)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7051. Min Range: -2.7051
Max Act: 2.2493. Min Act: -0.0000
Data Index: 1221276 (The Pile)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7051. Min Range: -2.7051
Max Act: 1.9398. Min Act: -0.0000
Data Index: 83492 (The Pile)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7051. Min Range: -2.7051
Max Act: 2.0129. Min Act: -0.0000
Data Index: 1693748 (The Pile)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7051. Min Range: -2.7051
Max Act: 2.0939. Min Act: -0.0000
Data Index: 783204 (The Pile)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7051. Min Range: -2.7051
Max Act: 2.0839. Min Act: -0.0000
Data Index: 1453040 (The Pile)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7051. Min Range: -2.7051
Max Act: 2.1753. Min Act: -0.0000
Data Index: 1080738 (The Pile)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7051. Min Range: -2.7051
Max Act: 2.0631. Min Act: -0.0000
Data Index: 1666621 (The Pile)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7051. Min Range: -2.7051
Max Act: 2.1654. Min Act: -0.0000
Data Index: 1539635 (The Pile)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7051. Min Range: -2.7051
Max Act: 2.0670. Min Act: -0.0000
Data Index: 992759 (The Pile)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7051. Min Range: -2.7051
Max Act: 1.9327. Min Act: -0.0000
Data Index: 373723 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7051. Min Range: -2.7051
Max Act: 2.0337. Min Act: -0.0000
Data Index: 1928709 (The Pile)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7051. Min Range: -2.7051
Max Act: 2.0245. Min Act: -0.0000
Data Index: 643526 (The Pile)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19