Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1471 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.6204. Min Range: -1.6204
Max Act: 1.6204. Min Act: -0.0001
Data Index: 194606 (The Pile)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6204. Min Range: -1.6204
Max Act: 1.5791. Min Act: -0.0001
Data Index: 26466 (The Pile)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6204. Min Range: -1.6204
Max Act: 1.5701. Min Act: -0.0001
Data Index: 1225535 (The Pile)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6204. Min Range: -1.6204
Max Act: 1.4497. Min Act: -0.0001
Data Index: 42082 (The Pile)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6204. Min Range: -1.6204
Max Act: 1.3305. Min Act: -0.0001
Data Index: 1163032 (The Pile)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6204. Min Range: -1.6204
Max Act: 1.3033. Min Act: -0.0001
Data Index: 1701886 (The Pile)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6204. Min Range: -1.6204
Max Act: 1.3768. Min Act: -0.0001
Data Index: 668644 (The Pile)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6204. Min Range: -1.6204
Max Act: 1.1699. Min Act: -0.0001
Data Index: 59133 (The Pile)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6204. Min Range: -1.6204
Max Act: 1.3051. Min Act: -0.0001
Data Index: 877060 (The Pile)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6204. Min Range: -1.6204
Max Act: 1.3301. Min Act: -0.0001
Data Index: 1003404 (The Pile)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6204. Min Range: -1.6204
Max Act: 1.2200. Min Act: -0.0001
Data Index: 48959 (The Pile)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6204. Min Range: -1.6204
Max Act: 1.2585. Min Act: -0.0001
Data Index: 826486 (The Pile)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6204. Min Range: -1.6204
Max Act: 1.4313. Min Act: -0.0001
Data Index: 954053 (The Pile)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6204. Min Range: -1.6204
Max Act: 1.2643. Min Act: -0.0001
Data Index: 292253 (The Pile)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6204. Min Range: -1.6204
Max Act: 1.3148. Min Act: -0.0001
Data Index: 527529 (The Pile)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6204. Min Range: -1.6204
Max Act: 1.2874. Min Act: -0.0001
Data Index: 633435 (The Pile)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6204. Min Range: -1.6204
Max Act: 1.2092. Min Act: -0.0001
Data Index: 1933545 (The Pile)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6204. Min Range: -1.6204
Max Act: 1.1183. Min Act: -0.0001
Data Index: 901662 (The Pile)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6204. Min Range: -1.6204
Max Act: 1.2571. Min Act: -0.0001
Data Index: 530730 (The Pile)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6204. Min Range: -1.6204
Max Act: 1.2359. Min Act: -0.0001
Data Index: 1820305 (The Pile)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19