Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2660 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.2759. Min Range: -0.2759
Max Act: 0.2759. Min Act: -0.0001
Data Index: 993790 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2759. Min Range: -0.2759
Max Act: 0.2547. Min Act: -0.0001
Data Index: 987496 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2759. Min Range: -0.2759
Max Act: 0.2146. Min Act: -0.0001
Data Index: 1192103 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2759. Min Range: -0.2759
Max Act: 0.2204. Min Act: -0.0001
Data Index: 283108 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2759. Min Range: -0.2759
Max Act: 0.1971. Min Act: -0.0001
Data Index: 1121118 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2759. Min Range: -0.2759
Max Act: 0.2022. Min Act: -0.0001
Data Index: 529877 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2759. Min Range: -0.2759
Max Act: 0.1946. Min Act: -0.0001
Data Index: 1141664 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2759. Min Range: -0.2759
Max Act: 0.1735. Min Act: -0.0001
Data Index: 286051 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2759. Min Range: -0.2759
Max Act: 0.1882. Min Act: -0.0001
Data Index: 696327 (C4 (Web Text))
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2759. Min Range: -0.2759
Max Act: 0.1915. Min Act: -0.0001
Data Index: 1314700 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2759. Min Range: -0.2759
Max Act: 0.1841. Min Act: -0.0001
Data Index: 1110749 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2759. Min Range: -0.2759
Max Act: 0.1904. Min Act: -0.0001
Data Index: 752849 (C4 (Web Text))
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2759. Min Range: -0.2759
Max Act: 0.1838. Min Act: -0.0001
Data Index: 261442 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2759. Min Range: -0.2759
Max Act: 0.1852. Min Act: -0.0001
Data Index: 1337870 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2759. Min Range: -0.2759
Max Act: 0.1853. Min Act: -0.0001
Data Index: 232429 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2759. Min Range: -0.2759
Max Act: 0.1839. Min Act: -0.0001
Data Index: 174735 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2759. Min Range: -0.2759
Max Act: 0.1771. Min Act: -0.0001
Data Index: 628541 (C4 (Web Text))
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2759. Min Range: -0.2759
Max Act: 0.1838. Min Act: -0.0001
Data Index: 1168000 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2759. Min Range: -0.2759
Max Act: 0.1732. Min Act: -0.0001
Data Index: 299901 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2759. Min Range: -0.2759
Max Act: 0.1794. Min Act: -0.0001
Data Index: 38875 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19