Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 728 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.0917. Min Range: -0.0917
Max Act: 0.0917. Min Act: -0.0001
Data Index: 720362 (C4 (Web Text))
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0917. Min Range: -0.0917
Max Act: 0.0584. Min Act: -0.0001
Data Index: 427933 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0917. Min Range: -0.0917
Max Act: 0.0599. Min Act: -0.0001
Data Index: 1647154 (Python Code)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0917. Min Range: -0.0917
Max Act: 0.0527. Min Act: -0.0001
Data Index: 489298 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0917. Min Range: -0.0917
Max Act: 0.0512. Min Act: -0.0001
Data Index: 877171 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0917. Min Range: -0.0917
Max Act: 0.0543. Min Act: -0.0001
Data Index: 795189 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0917. Min Range: -0.0917
Max Act: 0.0557. Min Act: -0.0001
Data Index: 1451085 (Python Code)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0917. Min Range: -0.0917
Max Act: 0.0567. Min Act: -0.0001
Data Index: 612838 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0917. Min Range: -0.0917
Max Act: 0.0509. Min Act: -0.0001
Data Index: 524738 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0917. Min Range: -0.0917
Max Act: 0.0557. Min Act: -0.0001
Data Index: 823980 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0917. Min Range: -0.0917
Max Act: 0.0446. Min Act: -0.0001
Data Index: 341399 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0917. Min Range: -0.0917
Max Act: 0.0523. Min Act: -0.0001
Data Index: 1116442 (C4 (Web Text))
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0917. Min Range: -0.0917
Max Act: 0.0461. Min Act: -0.0001
Data Index: 434690 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0917. Min Range: -0.0917
Max Act: 0.0495. Min Act: -0.0001
Data Index: 1001974 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0917. Min Range: -0.0917
Max Act: 0.0513. Min Act: -0.0001
Data Index: 1224565 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0917. Min Range: -0.0917
Max Act: 0.0571. Min Act: -0.0001
Data Index: 801550 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0917. Min Range: -0.0917
Max Act: 0.0519. Min Act: -0.0001
Data Index: 1089829 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0917. Min Range: -0.0917
Max Act: 0.0559. Min Act: -0.0001
Data Index: 875441 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0917. Min Range: -0.0917
Max Act: 0.0581. Min Act: -0.0001
Data Index: 609492 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0917. Min Range: -0.0917
Max Act: 0.0562. Min Act: -0.0001
Data Index: 652430 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19