Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2371 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 3.0816. Min Range: -3.0816
Max Act: 3.0816. Min Act: -0.0001
Data Index: 20440 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0816. Min Range: -3.0816
Max Act: 2.7230. Min Act: -0.0001
Data Index: 1120775 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0816. Min Range: -3.0816
Max Act: 2.3530. Min Act: -0.0001
Data Index: 421478 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0816. Min Range: -3.0816
Max Act: 2.3822. Min Act: -0.0001
Data Index: 170695 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0816. Min Range: -3.0816
Max Act: 2.1442. Min Act: -0.0001
Data Index: 465639 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0816. Min Range: -3.0816
Max Act: 2.1496. Min Act: -0.0001
Data Index: 621708 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0816. Min Range: -3.0816
Max Act: 2.1162. Min Act: -0.0001
Data Index: 449670 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0816. Min Range: -3.0816
Max Act: 2.1333. Min Act: -0.0001
Data Index: 768025 (C4 (Web Text))
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0816. Min Range: -3.0816
Max Act: 2.0155. Min Act: -0.0001
Data Index: 589017 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0816. Min Range: -3.0816
Max Act: 1.9877. Min Act: -0.0001
Data Index: 1125240 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0816. Min Range: -3.0816
Max Act: 2.1999. Min Act: -0.0001
Data Index: 1310376 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0816. Min Range: -3.0816
Max Act: 2.1897. Min Act: -0.0001
Data Index: 1171962 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0816. Min Range: -3.0816
Max Act: 2.0386. Min Act: -0.0001
Data Index: 8796 (C4 (Web Text))
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0816. Min Range: -3.0816
Max Act: 2.0716. Min Act: -0.0001
Data Index: 717779 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0816. Min Range: -3.0816
Max Act: 2.0034. Min Act: -0.0001
Data Index: 568010 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0816. Min Range: -3.0816
Max Act: 1.9647. Min Act: -0.0001
Data Index: 1141216 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0816. Min Range: -3.0816
Max Act: 1.6840. Min Act: -0.0001
Data Index: 1048521 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0816. Min Range: -3.0816
Max Act: 2.0379. Min Act: -0.0001
Data Index: 102953 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0816. Min Range: -3.0816
Max Act: 1.9295. Min Act: -0.0001
Data Index: 932244 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0816. Min Range: -3.0816
Max Act: 1.9614. Min Act: -0.0001
Data Index: 1091432 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19