Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3568 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.0723. Min Range: -2.0723
Max Act: 2.0723. Min Act: -0.0001
Data Index: 884700 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0723. Min Range: -2.0723
Max Act: 2.0215. Min Act: -0.0001
Data Index: 820730 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.8146. Min Act: -0.0001
Data Index: 1297724 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.7859. Min Act: -0.0001
Data Index: 110693 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.8423. Min Act: -0.0001
Data Index: 208213 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.6971. Min Act: -0.0001
Data Index: 811961 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.8686. Min Act: -0.0001
Data Index: 1136876 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.7272. Min Act: -0.0001
Data Index: 765379 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.7347. Min Act: -0.0001
Data Index: 1022747 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.8297. Min Act: -0.0001
Data Index: 265143 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.6736. Min Act: -0.0001
Data Index: 414762 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.5463. Min Act: -0.0001
Data Index: 993797 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.5304. Min Act: -0.0001
Data Index: 145751 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.6825. Min Act: -0.0001
Data Index: 701654 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.6206. Min Act: -0.0001
Data Index: 1330928 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.5952. Min Act: -0.0001
Data Index: 559699 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.7374. Min Act: -0.0001
Data Index: 523590 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.4012. Min Act: -0.0001
Data Index: 1073353 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.6732. Min Act: -0.0001
Data Index: 56212 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0723. Min Range: -2.0723
Max Act: 1.3615. Min Act: -0.0001
Data Index: 1068661 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19