Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3537 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.6766. Min Act: -0.0001
Data Index: 1495356 (Python Code)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.2025. Min Act: -0.0001
Data Index: 1472491 (Python Code)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.2563. Min Act: -0.0001
Data Index: 1394285 (Python Code)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.3611. Min Act: -0.0001
Data Index: 1643283 (Python Code)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.2542. Min Act: -0.0001
Data Index: 1590194 (Python Code)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.0470. Min Act: -0.0001
Data Index: 1565782 (Python Code)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.1972. Min Act: -0.0001
Data Index: 1542006 (Python Code)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.1431. Min Act: -0.0001
Data Index: 1363625 (Python Code)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.0838. Min Act: -0.0001
Data Index: 1555841 (Python Code)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.0552. Min Act: -0.0001
Data Index: 1560373 (Python Code)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.1062. Min Act: -0.0001
Data Index: 1363173 (Python Code)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.0870. Min Act: -0.0001
Data Index: 1584130 (Python Code)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6766. Min Range: -2.6766
Max Act: 1.9261. Min Act: -0.0001
Data Index: 1560163 (Python Code)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.3057. Min Act: -0.0001
Data Index: 1581164 (Python Code)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.1058. Min Act: -0.0001
Data Index: 1456470 (Python Code)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.0397. Min Act: -0.0001
Data Index: 1422251 (Python Code)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.0351. Min Act: -0.0001
Data Index: 1627985 (Python Code)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6766. Min Range: -2.6766
Max Act: 1.9754. Min Act: -0.0001
Data Index: 1485720 (Python Code)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.0281. Min Act: -0.0001
Data Index: 1366441 (Python Code)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6766. Min Range: -2.6766
Max Act: 1.9623. Min Act: -0.0001
Data Index: 1566357 (Python Code)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19