Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3485 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.0989. Min Range: -0.0989
Max Act: 0.0989. Min Act: -0.0001
Data Index: 1334281 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0989. Min Range: -0.0989
Max Act: 0.0925. Min Act: -0.0001
Data Index: 822358 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0989. Min Range: -0.0989
Max Act: 0.0784. Min Act: -0.0001
Data Index: 1532225 (Python Code)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0989. Min Range: -0.0989
Max Act: 0.0844. Min Act: -0.0001
Data Index: 576586 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0989. Min Range: -0.0989
Max Act: 0.0814. Min Act: -0.0001
Data Index: 1279452 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0989. Min Range: -0.0989
Max Act: 0.0866. Min Act: -0.0001
Data Index: 1053812 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0989. Min Range: -0.0989
Max Act: 0.0767. Min Act: -0.0001
Data Index: 441830 (C4 (Web Text))
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0989. Min Range: -0.0989
Max Act: 0.0749. Min Act: -0.0001
Data Index: 950848 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0989. Min Range: -0.0989
Max Act: 0.0835. Min Act: -0.0001
Data Index: 100118 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0989. Min Range: -0.0989
Max Act: 0.0749. Min Act: -0.0001
Data Index: 563572 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0989. Min Range: -0.0989
Max Act: 0.0763. Min Act: -0.0001
Data Index: 1020284 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0989. Min Range: -0.0989
Max Act: 0.0738. Min Act: -0.0001
Data Index: 896962 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0989. Min Range: -0.0989
Max Act: 0.0764. Min Act: -0.0001
Data Index: 1332356 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0989. Min Range: -0.0989
Max Act: 0.0584. Min Act: -0.0001
Data Index: 1629055 (Python Code)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0989. Min Range: -0.0989
Max Act: 0.0745. Min Act: -0.0001
Data Index: 1009020 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0989. Min Range: -0.0989
Max Act: 0.0776. Min Act: -0.0001
Data Index: 280207 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0989. Min Range: -0.0989
Max Act: 0.0711. Min Act: -0.0001
Data Index: 1114696 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0989. Min Range: -0.0989
Max Act: 0.0736. Min Act: -0.0001
Data Index: 811271 (C4 (Web Text))
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0989. Min Range: -0.0989
Max Act: 0.0723. Min Act: -0.0001
Data Index: 157731 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0989. Min Range: -0.0989
Max Act: 0.0762. Min Act: -0.0001
Data Index: 1265011 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19