Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2324 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 9.7016. Min Range: -9.7016
Max Act: 9.7016. Min Act: 0.0001
Data Index: 1870544 (The Pile)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7016. Min Range: -9.7016
Max Act: 9.2687. Min Act: 0.0000
Data Index: 1742768 (The Pile)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7016. Min Range: -9.7016
Max Act: 9.0676. Min Act: -0.0000
Data Index: 1159105 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7016. Min Range: -9.7016
Max Act: 8.9481. Min Act: -0.0000
Data Index: 1076389 (The Pile)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7016. Min Range: -9.7016
Max Act: 9.0860. Min Act: 0.0001
Data Index: 1776781 (The Pile)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7016. Min Range: -9.7016
Max Act: 9.0616. Min Act: 0.0000
Data Index: 798234 (The Pile)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7016. Min Range: -9.7016
Max Act: 8.8415. Min Act: -0.0000
Data Index: 1161259 (The Pile)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7016. Min Range: -9.7016
Max Act: 8.8857. Min Act: -0.0000
Data Index: 1810207 (The Pile)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7016. Min Range: -9.7016
Max Act: 8.8555. Min Act: 0.0001
Data Index: 1513441 (The Pile)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7016. Min Range: -9.7016
Max Act: 8.8323. Min Act: 0.0001
Data Index: 298339 (The Pile)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7016. Min Range: -9.7016
Max Act: 8.7759. Min Act: -0.0000
Data Index: 1051045 (The Pile)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7016. Min Range: -9.7016
Max Act: 8.5900. Min Act: 0.0001
Data Index: 1601331 (The Pile)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7016. Min Range: -9.7016
Max Act: 8.7143. Min Act: 0.0001
Data Index: 1834845 (The Pile)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7016. Min Range: -9.7016
Max Act: 8.7323. Min Act: 0.0001
Data Index: 1999327 (The Pile)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7016. Min Range: -9.7016
Max Act: 8.7265. Min Act: 0.0001
Data Index: 962325 (The Pile)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7016. Min Range: -9.7016
Max Act: 8.4904. Min Act: 0.0001
Data Index: 1978607 (The Pile)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7016. Min Range: -9.7016
Max Act: 8.6805. Min Act: 0.0001
Data Index: 352530 (The Pile)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7016. Min Range: -9.7016
Max Act: 8.6574. Min Act: 0.0000
Data Index: 1799629 (The Pile)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7016. Min Range: -9.7016
Max Act: 8.6374. Min Act: 0.0001
Data Index: 1771290 (The Pile)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7016. Min Range: -9.7016
Max Act: 8.4435. Min Act: 0.0000
Data Index: 17246 (The Pile)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19