Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1104 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.4370. Min Range: -0.4370
Max Act: 0.4370. Min Act: -0.0001
Data Index: 564385 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4370. Min Range: -0.4370
Max Act: 0.4333. Min Act: -0.0001
Data Index: 1191973 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4370. Min Range: -0.4370
Max Act: 0.4139. Min Act: -0.0001
Data Index: 775057 (C4 (Web Text))
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4370. Min Range: -0.4370
Max Act: 0.4156. Min Act: -0.0001
Data Index: 631198 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4370. Min Range: -0.4370
Max Act: 0.4004. Min Act: -0.0001
Data Index: 672728 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4370. Min Range: -0.4370
Max Act: 0.4097. Min Act: -0.0001
Data Index: 357215 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4370. Min Range: -0.4370
Max Act: 0.3808. Min Act: -0.0001
Data Index: 450550 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4370. Min Range: -0.4370
Max Act: 0.3880. Min Act: -0.0001
Data Index: 670542 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4370. Min Range: -0.4370
Max Act: 0.4148. Min Act: -0.0001
Data Index: 42097 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4370. Min Range: -0.4370
Max Act: 0.3806. Min Act: -0.0001
Data Index: 492154 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4370. Min Range: -0.4370
Max Act: 0.3689. Min Act: -0.0001
Data Index: 993099 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4370. Min Range: -0.4370
Max Act: 0.3643. Min Act: -0.0001
Data Index: 645352 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4370. Min Range: -0.4370
Max Act: 0.3788. Min Act: -0.0001
Data Index: 336777 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4370. Min Range: -0.4370
Max Act: 0.3642. Min Act: -0.0001
Data Index: 15700 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4370. Min Range: -0.4370
Max Act: 0.3724. Min Act: -0.0001
Data Index: 465170 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4370. Min Range: -0.4370
Max Act: 0.3839. Min Act: -0.0001
Data Index: 800915 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4370. Min Range: -0.4370
Max Act: 0.3728. Min Act: -0.0001
Data Index: 486648 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4370. Min Range: -0.4370
Max Act: 0.3571. Min Act: -0.0001
Data Index: 1343098 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4370. Min Range: -0.4370
Max Act: 0.3561. Min Act: -0.0001
Data Index: 1211415 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4370. Min Range: -0.4370
Max Act: 0.3562. Min Act: -0.0001
Data Index: 1138655 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19