Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2843 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.2599. Min Range: -1.2599
Max Act: 1.1640. Min Act: -0.0001
Data Index: 980842 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2599. Min Range: -1.2599
Max Act: 1.1403. Min Act: -0.0001
Data Index: 1293249 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2599. Min Range: -1.2599
Max Act: 1.0327. Min Act: -0.0001
Data Index: 324331 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2599. Min Range: -1.2599
Max Act: 1.2599. Min Act: -0.0001
Data Index: 885409 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2599. Min Range: -1.2599
Max Act: 1.0459. Min Act: -0.0001
Data Index: 171290 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2599. Min Range: -1.2599
Max Act: 1.1040. Min Act: -0.0001
Data Index: 667568 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2599. Min Range: -1.2599
Max Act: 1.1650. Min Act: -0.0001
Data Index: 231483 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2599. Min Range: -1.2599
Max Act: 1.1175. Min Act: -0.0001
Data Index: 89124 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2599. Min Range: -1.2599
Max Act: 1.2021. Min Act: -0.0001
Data Index: 1053808 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2599. Min Range: -1.2599
Max Act: 1.1076. Min Act: -0.0001
Data Index: 556781 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2599. Min Range: -1.2599
Max Act: 1.1259. Min Act: -0.0001
Data Index: 1076193 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2599. Min Range: -1.2599
Max Act: 1.1407. Min Act: -0.0001
Data Index: 526478 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2599. Min Range: -1.2599
Max Act: 1.1665. Min Act: -0.0001
Data Index: 932815 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2599. Min Range: -1.2599
Max Act: 1.1128. Min Act: -0.0001
Data Index: 189932 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2599. Min Range: -1.2599
Max Act: 1.1055. Min Act: -0.0001
Data Index: 1313304 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2599. Min Range: -1.2599
Max Act: 1.0558. Min Act: -0.0001
Data Index: 856680 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2599. Min Range: -1.2599
Max Act: 1.0799. Min Act: -0.0001
Data Index: 31747 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2599. Min Range: -1.2599
Max Act: 1.0408. Min Act: -0.0001
Data Index: 496222 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2599. Min Range: -1.2599
Max Act: 1.0722. Min Act: -0.0001
Data Index: 1348530 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2599. Min Range: -1.2599
Max Act: 1.0824. Min Act: -0.0001
Data Index: 271783 (C4 (Web Text))
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19