Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1235 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.1061. Min Range: -0.1061
Max Act: 0.1061. Min Act: -0.0001
Data Index: 1235230 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1061. Min Range: -0.1061
Max Act: 0.1042. Min Act: -0.0001
Data Index: 544536 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1061. Min Range: -0.1061
Max Act: 0.0989. Min Act: -0.0001
Data Index: 197109 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1061. Min Range: -0.1061
Max Act: 0.0889. Min Act: -0.0001
Data Index: 780591 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1061. Min Range: -0.1061
Max Act: 0.0840. Min Act: -0.0001
Data Index: 1338687 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1061. Min Range: -0.1061
Max Act: 0.0851. Min Act: -0.0001
Data Index: 476461 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1061. Min Range: -0.1061
Max Act: 0.0844. Min Act: -0.0001
Data Index: 1166167 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1061. Min Range: -0.1061
Max Act: 0.0824. Min Act: -0.0001
Data Index: 1388742 (Python Code)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1061. Min Range: -0.1061
Max Act: 0.0814. Min Act: -0.0001
Data Index: 271646 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1061. Min Range: -0.1061
Max Act: 0.0781. Min Act: -0.0001
Data Index: 1000090 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1061. Min Range: -0.1061
Max Act: 0.0777. Min Act: -0.0001
Data Index: 276233 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1061. Min Range: -0.1061
Max Act: 0.0749. Min Act: -0.0001
Data Index: 1382767 (Python Code)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1061. Min Range: -0.1061
Max Act: 0.0823. Min Act: -0.0001
Data Index: 1224 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1061. Min Range: -0.1061
Max Act: 0.0713. Min Act: -0.0001
Data Index: 1598169 (Python Code)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1061. Min Range: -0.1061
Max Act: 0.0733. Min Act: -0.0001
Data Index: 133569 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1061. Min Range: -0.1061
Max Act: 0.0804. Min Act: -0.0001
Data Index: 1504984 (Python Code)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1061. Min Range: -0.1061
Max Act: 0.0760. Min Act: -0.0001
Data Index: 589378 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1061. Min Range: -0.1061
Max Act: 0.0774. Min Act: -0.0001
Data Index: 190991 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1061. Min Range: -0.1061
Max Act: 0.0761. Min Act: -0.0001
Data Index: 665086 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1061. Min Range: -0.1061
Max Act: 0.0786. Min Act: -0.0001
Data Index: 641545 (C4 (Web Text))
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19