Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 900 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.3689. Min Range: -2.3689
Max Act: 2.3689. Min Act: -0.0000
Data Index: 1018350 (The Pile)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3689. Min Range: -2.3689
Max Act: 2.2736. Min Act: -0.0000
Data Index: 1925140 (The Pile)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3689. Min Range: -2.3689
Max Act: 2.2146. Min Act: -0.0000
Data Index: 1256003 (The Pile)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3689. Min Range: -2.3689
Max Act: 2.1307. Min Act: -0.0000
Data Index: 942459 (The Pile)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3689. Min Range: -2.3689
Max Act: 2.2903. Min Act: -0.0000
Data Index: 1830243 (The Pile)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3689. Min Range: -2.3689
Max Act: 2.1149. Min Act: -0.0000
Data Index: 794508 (The Pile)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3689. Min Range: -2.3689
Max Act: 1.8700. Min Act: -0.0000
Data Index: 347114 (The Pile)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3689. Min Range: -2.3689
Max Act: 1.9584. Min Act: -0.0000
Data Index: 474032 (The Pile)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3689. Min Range: -2.3689
Max Act: 1.9598. Min Act: -0.0000
Data Index: 8274 (The Pile)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3689. Min Range: -2.3689
Max Act: 2.0495. Min Act: -0.0000
Data Index: 1341325 (The Pile)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3689. Min Range: -2.3689
Max Act: 1.9281. Min Act: -0.0000
Data Index: 500646 (The Pile)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3689. Min Range: -2.3689
Max Act: 1.8074. Min Act: -0.0000
Data Index: 552881 (The Pile)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3689. Min Range: -2.3689
Max Act: 1.9067. Min Act: -0.0000
Data Index: 97462 (The Pile)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3689. Min Range: -2.3689
Max Act: 2.0100. Min Act: -0.0000
Data Index: 1018148 (The Pile)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3689. Min Range: -2.3689
Max Act: 2.0001. Min Act: -0.0000
Data Index: 1125403 (The Pile)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3689. Min Range: -2.3689
Max Act: 1.9993. Min Act: -0.0000
Data Index: 1522669 (The Pile)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3689. Min Range: -2.3689
Max Act: 1.8853. Min Act: -0.0000
Data Index: 324175 (The Pile)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3689. Min Range: -2.3689
Max Act: 1.8871. Min Act: -0.0000
Data Index: 693803 (The Pile)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3689. Min Range: -2.3689
Max Act: 2.0738. Min Act: -0.0000
Data Index: 946583 (The Pile)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3689. Min Range: -2.3689
Max Act: 1.9759. Min Act: -0.0000
Data Index: 1996395 (The Pile)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19