Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 3293 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.7033. Min Range: -1.7033
Max Act: 1.5569. Min Act: -0.0000
Data Index: 820325 (The Pile)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7033. Min Range: -1.7033
Max Act: 1.6418. Min Act: -0.0000
Data Index: 538433 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7033. Min Range: -1.7033
Max Act: 1.6213. Min Act: -0.0000
Data Index: 1305095 (The Pile)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7033. Min Range: -1.7033
Max Act: 1.4515. Min Act: -0.0000
Data Index: 859158 (The Pile)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7033. Min Range: -1.7033
Max Act: 1.7033. Min Act: -0.0000
Data Index: 1474705 (The Pile)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7033. Min Range: -1.7033
Max Act: 1.6173. Min Act: -0.0000
Data Index: 974083 (The Pile)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7033. Min Range: -1.7033
Max Act: 1.2487. Min Act: -0.0000
Data Index: 1710410 (The Pile)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7033. Min Range: -1.7033
Max Act: 1.4828. Min Act: -0.0000
Data Index: 1052777 (The Pile)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7033. Min Range: -1.7033
Max Act: 1.3854. Min Act: -0.0000
Data Index: 1105027 (The Pile)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7033. Min Range: -1.7033
Max Act: 1.2502. Min Act: -0.0000
Data Index: 750044 (The Pile)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7033. Min Range: -1.7033
Max Act: 1.4232. Min Act: -0.0000
Data Index: 1919225 (The Pile)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7033. Min Range: -1.7033
Max Act: 1.2812. Min Act: -0.0000
Data Index: 826089 (The Pile)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7033. Min Range: -1.7033
Max Act: 1.3655. Min Act: -0.0000
Data Index: 204308 (The Pile)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7033. Min Range: -1.7033
Max Act: 1.2078. Min Act: -0.0000
Data Index: 1446586 (The Pile)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7033. Min Range: -1.7033
Max Act: 1.2833. Min Act: -0.0000
Data Index: 336830 (The Pile)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7033. Min Range: -1.7033
Max Act: 1.1979. Min Act: -0.0000
Data Index: 339928 (The Pile)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7033. Min Range: -1.7033
Max Act: 1.1956. Min Act: -0.0000
Data Index: 655821 (The Pile)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7033. Min Range: -1.7033
Max Act: 1.4311. Min Act: -0.0000
Data Index: 1948780 (The Pile)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7033. Min Range: -1.7033
Max Act: 1.3107. Min Act: -0.0000
Data Index: 1975163 (The Pile)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7033. Min Range: -1.7033
Max Act: 1.2998. Min Act: -0.0000
Data Index: 744326 (The Pile)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19