Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2980 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.3635. Min Range: -2.3635
Max Act: 2.3605. Min Act: -0.0000
Data Index: 594246 (The Pile)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3635. Min Range: -2.3635
Max Act: 2.3635. Min Act: -0.0000
Data Index: 374599 (The Pile)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3635. Min Range: -2.3635
Max Act: 2.2066. Min Act: -0.0000
Data Index: 1624667 (The Pile)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3635. Min Range: -2.3635
Max Act: 2.1708. Min Act: -0.0000
Data Index: 232383 (The Pile)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3635. Min Range: -2.3635
Max Act: 2.0138. Min Act: -0.0000
Data Index: 738348 (The Pile)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3635. Min Range: -2.3635
Max Act: 2.0973. Min Act: -0.0000
Data Index: 1653974 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3635. Min Range: -2.3635
Max Act: 2.0755. Min Act: -0.0000
Data Index: 462594 (The Pile)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3635. Min Range: -2.3635
Max Act: 1.9564. Min Act: -0.0000
Data Index: 1092336 (The Pile)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3635. Min Range: -2.3635
Max Act: 1.9988. Min Act: -0.0000
Data Index: 847831 (The Pile)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3635. Min Range: -2.3635
Max Act: 2.0768. Min Act: -0.0000
Data Index: 1449366 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3635. Min Range: -2.3635
Max Act: 1.9690. Min Act: -0.0000
Data Index: 1177740 (The Pile)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3635. Min Range: -2.3635
Max Act: 1.9691. Min Act: -0.0000
Data Index: 1659155 (The Pile)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3635. Min Range: -2.3635
Max Act: 1.8339. Min Act: -0.0000
Data Index: 1926520 (The Pile)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3635. Min Range: -2.3635
Max Act: 1.9300. Min Act: -0.0000
Data Index: 702016 (The Pile)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3635. Min Range: -2.3635
Max Act: 1.9312. Min Act: -0.0000
Data Index: 234903 (The Pile)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3635. Min Range: -2.3635
Max Act: 1.8263. Min Act: -0.0000
Data Index: 1817582 (The Pile)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3635. Min Range: -2.3635
Max Act: 2.0161. Min Act: -0.0000
Data Index: 1795845 (The Pile)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3635. Min Range: -2.3635
Max Act: 2.1116. Min Act: -0.0000
Data Index: 158471 (The Pile)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3635. Min Range: -2.3635
Max Act: 1.9967. Min Act: -0.0000
Data Index: 1559723 (The Pile)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3635. Min Range: -2.3635
Max Act: 1.7757. Min Act: -0.0000
Data Index: 1962788 (The Pile)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19