Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 67 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.3976. Min Range: -3.3976
Max Act: 3.3976. Min Act: -0.0002
Data Index: 1539139 (Python Code)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3976. Min Range: -3.3976
Max Act: 2.6325. Min Act: -0.0002
Data Index: 1373599 (Python Code)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3976. Min Range: -3.3976
Max Act: 1.9960. Min Act: -0.0002
Data Index: 1627550 (Python Code)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3976. Min Range: -3.3976
Max Act: 2.1617. Min Act: -0.0002
Data Index: 1427771 (Python Code)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3976. Min Range: -3.3976
Max Act: 2.5734. Min Act: -0.0002
Data Index: 1578044 (Python Code)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3976. Min Range: -3.3976
Max Act: 2.2220. Min Act: -0.0002
Data Index: 1443600 (Python Code)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3976. Min Range: -3.3976
Max Act: 1.7511. Min Act: -0.0002
Data Index: 1370883 (Python Code)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3976. Min Range: -3.3976
Max Act: 2.0757. Min Act: -0.0002
Data Index: 1470388 (Python Code)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3976. Min Range: -3.3976
Max Act: 2.1087. Min Act: -0.0002
Data Index: 1591546 (Python Code)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3976. Min Range: -3.3976
Max Act: 1.6428. Min Act: -0.0002
Data Index: 1614316 (Python Code)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3976. Min Range: -3.3976
Max Act: 1.9706. Min Act: -0.0002
Data Index: 1577968 (Python Code)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3976. Min Range: -3.3976
Max Act: 2.2201. Min Act: -0.0002
Data Index: 1381883 (Python Code)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3976. Min Range: -3.3976
Max Act: 1.9758. Min Act: -0.0002
Data Index: 1591909 (Python Code)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3976. Min Range: -3.3976
Max Act: 2.1225. Min Act: -0.0002
Data Index: 1475016 (Python Code)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3976. Min Range: -3.3976
Max Act: 1.9762. Min Act: -0.0002
Data Index: 1422933 (Python Code)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3976. Min Range: -3.3976
Max Act: 2.0571. Min Act: -0.0002
Data Index: 1574887 (Python Code)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3976. Min Range: -3.3976
Max Act: 2.0753. Min Act: -0.0002
Data Index: 1374232 (Python Code)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3976. Min Range: -3.3976
Max Act: 2.0613. Min Act: -0.0002
Data Index: 1510933 (Python Code)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3976. Min Range: -3.3976
Max Act: 1.5761. Min Act: -0.0002
Data Index: 1433984 (Python Code)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3976. Min Range: -3.3976
Max Act: 1.4772. Min Act: -0.0002
Data Index: 1611442 (Python Code)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #19