Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3482 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.9650. Min Range: -2.9650
Max Act: 2.9650. Min Act: -0.0001
Data Index: 1477576 (Python Code)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9650. Min Range: -2.9650
Max Act: 2.7004. Min Act: -0.0001
Data Index: 1490627 (Python Code)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9650. Min Range: -2.9650
Max Act: 2.7909. Min Act: -0.0001
Data Index: 1519805 (Python Code)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9650. Min Range: -2.9650
Max Act: 2.7805. Min Act: -0.0001
Data Index: 1538600 (Python Code)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9650. Min Range: -2.9650
Max Act: 2.8948. Min Act: -0.0001
Data Index: 1452684 (Python Code)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9650. Min Range: -2.9650
Max Act: 2.6128. Min Act: -0.0001
Data Index: 1435358 (Python Code)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9650. Min Range: -2.9650
Max Act: 2.5737. Min Act: -0.0001
Data Index: 1382187 (Python Code)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9650. Min Range: -2.9650
Max Act: 2.5830. Min Act: -0.0001
Data Index: 1538415 (Python Code)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9650. Min Range: -2.9650
Max Act: 2.8243. Min Act: -0.0001
Data Index: 1507380 (Python Code)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9650. Min Range: -2.9650
Max Act: 2.8116. Min Act: -0.0001
Data Index: 1413265 (Python Code)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9650. Min Range: -2.9650
Max Act: 2.6739. Min Act: -0.0001
Data Index: 1425522 (Python Code)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9650. Min Range: -2.9650
Max Act: 2.5797. Min Act: -0.0001
Data Index: 1484815 (Python Code)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9650. Min Range: -2.9650
Max Act: 2.4060. Min Act: -0.0001
Data Index: 1371683 (Python Code)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9650. Min Range: -2.9650
Max Act: 2.6330. Min Act: -0.0001
Data Index: 1464859 (Python Code)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9650. Min Range: -2.9650
Max Act: 2.7446. Min Act: -0.0001
Data Index: 1501608 (Python Code)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9650. Min Range: -2.9650
Max Act: 2.4476. Min Act: -0.0001
Data Index: 1515332 (Python Code)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9650. Min Range: -2.9650
Max Act: 2.6764. Min Act: -0.0001
Data Index: 1468909 (Python Code)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9650. Min Range: -2.9650
Max Act: 2.5687. Min Act: -0.0001
Data Index: 1478974 (Python Code)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9650. Min Range: -2.9650
Max Act: 2.5253. Min Act: -0.0001
Data Index: 1530386 (Python Code)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9650. Min Range: -2.9650
Max Act: 2.5051. Min Act: -0.0001
Data Index: 1415845 (Python Code)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19