Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1040 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 4.2083. Min Range: -4.2083
Max Act: 4.0848. Min Act: -0.0001
Data Index: 631250 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2083. Min Range: -4.2083
Max Act: 4.2083. Min Act: -0.0001
Data Index: 198585 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2083. Min Range: -4.2083
Max Act: 3.6267. Min Act: -0.0001
Data Index: 230729 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2083. Min Range: -4.2083
Max Act: 3.3185. Min Act: -0.0001
Data Index: 479880 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2083. Min Range: -4.2083
Max Act: 3.4055. Min Act: -0.0001
Data Index: 227244 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2083. Min Range: -4.2083
Max Act: 3.3138. Min Act: -0.0001
Data Index: 500132 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2083. Min Range: -4.2083
Max Act: 3.1057. Min Act: -0.0001
Data Index: 535672 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2083. Min Range: -4.2083
Max Act: 2.9060. Min Act: -0.0001
Data Index: 918094 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2083. Min Range: -4.2083
Max Act: 2.5868. Min Act: -0.0001
Data Index: 167993 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2083. Min Range: -4.2083
Max Act: 3.0674. Min Act: -0.0001
Data Index: 1298012 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2083. Min Range: -4.2083
Max Act: 2.8666. Min Act: -0.0001
Data Index: 1044317 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2083. Min Range: -4.2083
Max Act: 2.4372. Min Act: -0.0001
Data Index: 427003 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2083. Min Range: -4.2083
Max Act: 2.7216. Min Act: -0.0001
Data Index: 317511 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2083. Min Range: -4.2083
Max Act: 2.3717. Min Act: -0.0001
Data Index: 1045390 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2083. Min Range: -4.2083
Max Act: 2.1150. Min Act: -0.0001
Data Index: 556058 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2083. Min Range: -4.2083
Max Act: 1.8265. Min Act: -0.0001
Data Index: 727190 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2083. Min Range: -4.2083
Max Act: 1.7121. Min Act: -0.0001
Data Index: 280184 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2083. Min Range: -4.2083
Max Act: 1.7474. Min Act: -0.0001
Data Index: 1280712 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2083. Min Range: -4.2083
Max Act: 1.7303. Min Act: -0.0001
Data Index: 427531 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2083. Min Range: -4.2083
Max Act: 1.7368. Min Act: -0.0001
Data Index: 922048 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19