Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3792 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.0927. Min Range: -2.0927
Max Act: 2.0927. Min Act: -0.0001
Data Index: 1370947 (Python Code)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0927. Min Range: -2.0927
Max Act: 1.9088. Min Act: -0.0001
Data Index: 1448297 (Python Code)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0927. Min Range: -2.0927
Max Act: 1.8151. Min Act: -0.0001
Data Index: 1569151 (Python Code)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0927. Min Range: -2.0927
Max Act: 1.8990. Min Act: -0.0001
Data Index: 1418992 (Python Code)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0927. Min Range: -2.0927
Max Act: 1.6750. Min Act: -0.0001
Data Index: 1511914 (Python Code)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0927. Min Range: -2.0927
Max Act: 1.7538. Min Act: -0.0001
Data Index: 1425455 (Python Code)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0927. Min Range: -2.0927
Max Act: 1.7051. Min Act: -0.0001
Data Index: 1622222 (Python Code)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0927. Min Range: -2.0927
Max Act: 1.4887. Min Act: -0.0001
Data Index: 742674 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0927. Min Range: -2.0927
Max Act: 1.6331. Min Act: -0.0001
Data Index: 1612686 (Python Code)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0927. Min Range: -2.0927
Max Act: 1.4372. Min Act: -0.0001
Data Index: 1434108 (Python Code)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0927. Min Range: -2.0927
Max Act: 1.6558. Min Act: -0.0001
Data Index: 1570258 (Python Code)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0927. Min Range: -2.0927
Max Act: 1.5615. Min Act: -0.0001
Data Index: 1564535 (Python Code)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0927. Min Range: -2.0927
Max Act: 1.4467. Min Act: -0.0001
Data Index: 1393733 (Python Code)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0927. Min Range: -2.0927
Max Act: 1.5930. Min Act: -0.0001
Data Index: 1625866 (Python Code)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0927. Min Range: -2.0927
Max Act: 1.5532. Min Act: -0.0001
Data Index: 1621740 (Python Code)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0927. Min Range: -2.0927
Max Act: 1.3902. Min Act: -0.0001
Data Index: 1455737 (Python Code)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0927. Min Range: -2.0927
Max Act: 1.3322. Min Act: -0.0001
Data Index: 1586998 (Python Code)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0927. Min Range: -2.0927
Max Act: 1.4075. Min Act: -0.0001
Data Index: 1535217 (Python Code)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0927. Min Range: -2.0927
Max Act: 1.4924. Min Act: -0.0001
Data Index: 1452508 (Python Code)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0927. Min Range: -2.0927
Max Act: 1.3955. Min Act: -0.0001
Data Index: 1651223 (Python Code)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #19