Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4827 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.8559. Min Range: -0.8559
Max Act: 0.8249. Min Act: -0.0001
Data Index: 89009 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8559. Min Range: -0.8559
Max Act: 0.8559. Min Act: -0.0001
Data Index: 702752 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8559. Min Range: -0.8559
Max Act: 0.8284. Min Act: -0.0001
Data Index: 75510 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8559. Min Range: -0.8559
Max Act: 0.8344. Min Act: -0.0001
Data Index: 1337411 (C4 (Web Text))
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8559. Min Range: -0.8559
Max Act: 0.7954. Min Act: -0.0001
Data Index: 931990 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8559. Min Range: -0.8559
Max Act: 0.7641. Min Act: -0.0001
Data Index: 1009730 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8559. Min Range: -0.8559
Max Act: 0.7386. Min Act: -0.0001
Data Index: 1240235 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8559. Min Range: -0.8559
Max Act: 0.7384. Min Act: -0.0001
Data Index: 442350 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8559. Min Range: -0.8559
Max Act: 0.7535. Min Act: -0.0001
Data Index: 1207636 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8559. Min Range: -0.8559
Max Act: 0.6682. Min Act: -0.0001
Data Index: 560087 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8559. Min Range: -0.8559
Max Act: 0.6675. Min Act: -0.0001
Data Index: 37450 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8559. Min Range: -0.8559
Max Act: 0.6081. Min Act: -0.0001
Data Index: 927316 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8559. Min Range: -0.8559
Max Act: 0.5841. Min Act: -0.0001
Data Index: 1208870 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8559. Min Range: -0.8559
Max Act: 0.5660. Min Act: -0.0001
Data Index: 137070 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8559. Min Range: -0.8559
Max Act: 0.5970. Min Act: -0.0001
Data Index: 548592 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8559. Min Range: -0.8559
Max Act: 0.5751. Min Act: -0.0001
Data Index: 419569 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8559. Min Range: -0.8559
Max Act: 0.5677. Min Act: -0.0001
Data Index: 856664 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8559. Min Range: -0.8559
Max Act: 0.5919. Min Act: -0.0001
Data Index: 201351 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8559. Min Range: -0.8559
Max Act: 0.5663. Min Act: -0.0001
Data Index: 903778 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8559. Min Range: -0.8559
Max Act: 0.5769. Min Act: -0.0001
Data Index: 748614 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19