Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2362 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.2228. Min Range: -1.2228
Max Act: 1.2228. Min Act: -0.0000
Data Index: 495335 (The Pile)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2228. Min Range: -1.2228
Max Act: 1.1636. Min Act: 0.0001
Data Index: 825079 (The Pile)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2228. Min Range: -1.2228
Max Act: 1.1847. Min Act: 0.0001
Data Index: 459012 (The Pile)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2228. Min Range: -1.2228
Max Act: 1.1791. Min Act: 0.0001
Data Index: 1237309 (The Pile)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2228. Min Range: -1.2228
Max Act: 1.0919. Min Act: -0.0000
Data Index: 1716674 (The Pile)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2228. Min Range: -1.2228
Max Act: 1.0852. Min Act: 0.0001
Data Index: 339334 (The Pile)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2228. Min Range: -1.2228
Max Act: 1.1047. Min Act: 0.0000
Data Index: 1499924 (The Pile)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2228. Min Range: -1.2228
Max Act: 1.1241. Min Act: -0.0000
Data Index: 36030 (The Pile)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2228. Min Range: -1.2228
Max Act: 1.0953. Min Act: -0.0000
Data Index: 283467 (The Pile)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2228. Min Range: -1.2228
Max Act: 1.0279. Min Act: -0.0000
Data Index: 199354 (The Pile)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2228. Min Range: -1.2228
Max Act: 1.0014. Min Act: 0.0000
Data Index: 1908254 (The Pile)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2228. Min Range: -1.2228
Max Act: 1.0718. Min Act: 0.0001
Data Index: 266106 (The Pile)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2228. Min Range: -1.2228
Max Act: 1.0664. Min Act: 0.0000
Data Index: 17821 (The Pile)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2228. Min Range: -1.2228
Max Act: 0.9930. Min Act: 0.0003
Data Index: 1350870 (The Pile)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2228. Min Range: -1.2228
Max Act: 0.9997. Min Act: -0.0000
Data Index: 1122797 (The Pile)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2228. Min Range: -1.2228
Max Act: 0.9691. Min Act: -0.0000
Data Index: 998824 (The Pile)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2228. Min Range: -1.2228
Max Act: 0.9597. Min Act: 0.0000
Data Index: 998269 (The Pile)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2228. Min Range: -1.2228
Max Act: 0.9530. Min Act: -0.0000
Data Index: 407076 (The Pile)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2228. Min Range: -1.2228
Max Act: 0.9920. Min Act: 0.0001
Data Index: 851814 (The Pile)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2228. Min Range: -1.2228
Max Act: 0.9384. Min Act: -0.0000
Data Index: 1895432 (The Pile)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19