Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3134 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.6691. Min Act: -0.0001
Data Index: 1641803 (Python Code)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.4847. Min Act: -0.0001
Data Index: 1449231 (Python Code)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.3050. Min Act: -0.0001
Data Index: 1597998 (Python Code)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.2874. Min Act: -0.0001
Data Index: 1598048 (Python Code)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.3391. Min Act: -0.0001
Data Index: 1540586 (Python Code)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.1832. Min Act: -0.0001
Data Index: 1492914 (Python Code)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.0272. Min Act: -0.0001
Data Index: 1039693 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.3265. Min Act: -0.0001
Data Index: 1402238 (Python Code)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.2053. Min Act: -0.0001
Data Index: 1369116 (Python Code)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.1760. Min Act: -0.0001
Data Index: 1550218 (Python Code)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.1439. Min Act: -0.0001
Data Index: 177285 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.1157. Min Act: -0.0001
Data Index: 1239953 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.0967. Min Act: -0.0001
Data Index: 1019056 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.0741. Min Act: -0.0001
Data Index: 328723 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.2581. Min Act: -0.0001
Data Index: 1513154 (Python Code)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.2725. Min Act: -0.0001
Data Index: 1515199 (Python Code)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.1796. Min Act: -0.0001
Data Index: 189569 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.0029. Min Act: -0.0001
Data Index: 1018651 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.0703. Min Act: -0.0001
Data Index: 570132 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.0284. Min Act: -0.0001
Data Index: 671181 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19