Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2560 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.0781. Min Range: -0.0781
Max Act: 0.0760. Min Act: -0.0001
Data Index: 290833 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0781. Min Range: -0.0781
Max Act: 0.0761. Min Act: -0.0001
Data Index: 1159157 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0781. Min Range: -0.0781
Max Act: 0.0777. Min Act: -0.0001
Data Index: 801545 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0781. Min Range: -0.0781
Max Act: 0.0723. Min Act: -0.0001
Data Index: 192750 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0781. Min Range: -0.0781
Max Act: 0.0781. Min Act: -0.0001
Data Index: 695069 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0781. Min Range: -0.0781
Max Act: 0.0722. Min Act: -0.0001
Data Index: 1412923 (Python Code)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0781. Min Range: -0.0781
Max Act: 0.0672. Min Act: -0.0001
Data Index: 361468 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0781. Min Range: -0.0781
Max Act: 0.0717. Min Act: -0.0001
Data Index: 788336 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0781. Min Range: -0.0781
Max Act: 0.0664. Min Act: -0.0001
Data Index: 483380 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0781. Min Range: -0.0781
Max Act: 0.0709. Min Act: -0.0001
Data Index: 300452 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0781. Min Range: -0.0781
Max Act: 0.0654. Min Act: -0.0001
Data Index: 359156 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0781. Min Range: -0.0781
Max Act: 0.0686. Min Act: -0.0001
Data Index: 113141 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0781. Min Range: -0.0781
Max Act: 0.0647. Min Act: -0.0001
Data Index: 388136 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0781. Min Range: -0.0781
Max Act: 0.0669. Min Act: -0.0001
Data Index: 569504 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0781. Min Range: -0.0781
Max Act: 0.0637. Min Act: -0.0001
Data Index: 465645 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0781. Min Range: -0.0781
Max Act: 0.0676. Min Act: -0.0001
Data Index: 1312392 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0781. Min Range: -0.0781
Max Act: 0.0659. Min Act: -0.0001
Data Index: 12381 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0781. Min Range: -0.0781
Max Act: 0.0656. Min Act: -0.0001
Data Index: 1009668 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0781. Min Range: -0.0781
Max Act: 0.0627. Min Act: -0.0001
Data Index: 984792 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0781. Min Range: -0.0781
Max Act: 0.0667. Min Act: -0.0001
Data Index: 1626503 (Python Code)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19