Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 2825 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.5597. Min Range: -0.5597
Max Act: 0.5597. Min Act: -0.0001
Data Index: 259137 (The Pile)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5597. Min Range: -0.5597
Max Act: 0.4076. Min Act: -0.0001
Data Index: 785860 (The Pile)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5597. Min Range: -0.5597
Max Act: 0.4118. Min Act: -0.0001
Data Index: 946995 (The Pile)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5597. Min Range: -0.5597
Max Act: 0.3308. Min Act: -0.0001
Data Index: 150490 (The Pile)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5597. Min Range: -0.5597
Max Act: 0.3810. Min Act: -0.0001
Data Index: 835076 (The Pile)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5597. Min Range: -0.5597
Max Act: 0.4050. Min Act: -0.0001
Data Index: 1851542 (The Pile)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5597. Min Range: -0.5597
Max Act: 0.3725. Min Act: -0.0001
Data Index: 304261 (The Pile)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5597. Min Range: -0.5597
Max Act: 0.3119. Min Act: -0.0001
Data Index: 345885 (The Pile)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5597. Min Range: -0.5597
Max Act: 0.4048. Min Act: -0.0001
Data Index: 1223018 (The Pile)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5597. Min Range: -0.5597
Max Act: 0.3454. Min Act: -0.0001
Data Index: 1736355 (The Pile)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5597. Min Range: -0.5597
Max Act: 0.3549. Min Act: -0.0001
Data Index: 1618800 (The Pile)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5597. Min Range: -0.5597
Max Act: 0.3930. Min Act: -0.0001
Data Index: 107543 (The Pile)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5597. Min Range: -0.5597
Max Act: 0.3585. Min Act: -0.0001
Data Index: 227029 (The Pile)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5597. Min Range: -0.5597
Max Act: 0.3790. Min Act: -0.0001
Data Index: 494118 (The Pile)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5597. Min Range: -0.5597
Max Act: 0.3712. Min Act: -0.0001
Data Index: 626436 (The Pile)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5597. Min Range: -0.5597
Max Act: 0.3594. Min Act: -0.0001
Data Index: 766126 (The Pile)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5597. Min Range: -0.5597
Max Act: 0.3423. Min Act: -0.0001
Data Index: 786335 (The Pile)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5597. Min Range: -0.5597
Max Act: 0.3046. Min Act: -0.0001
Data Index: 1995582 (The Pile)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5597. Min Range: -0.5597
Max Act: 0.3326. Min Act: -0.0001
Data Index: 1655248 (The Pile)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5597. Min Range: -0.5597
Max Act: 0.3388. Min Act: -0.0001
Data Index: 1243086 (The Pile)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19