Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1377 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.8492. Min Range: -2.8492
Max Act: 2.6925. Min Act: -0.0001
Data Index: 1571375 (Python Code)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8492. Min Range: -2.8492
Max Act: 2.8492. Min Act: -0.0001
Data Index: 1582217 (Python Code)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8492. Min Range: -2.8492
Max Act: 1.9759. Min Act: -0.0001
Data Index: 1601619 (Python Code)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8492. Min Range: -2.8492
Max Act: 2.0164. Min Act: -0.0001
Data Index: 1640377 (Python Code)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8492. Min Range: -2.8492
Max Act: 2.1642. Min Act: -0.0001
Data Index: 1546919 (Python Code)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8492. Min Range: -2.8492
Max Act: 1.9001. Min Act: -0.0001
Data Index: 1614770 (Python Code)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8492. Min Range: -2.8492
Max Act: 2.4266. Min Act: -0.0001
Data Index: 1609654 (Python Code)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8492. Min Range: -2.8492
Max Act: 2.1191. Min Act: -0.0001
Data Index: 1655040 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8492. Min Range: -2.8492
Max Act: 1.9091. Min Act: -0.0001
Data Index: 1544146 (Python Code)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8492. Min Range: -2.8492
Max Act: 1.9441. Min Act: -0.0001
Data Index: 1557535 (Python Code)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8492. Min Range: -2.8492
Max Act: 1.8630. Min Act: -0.0001
Data Index: 1524503 (Python Code)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8492. Min Range: -2.8492
Max Act: 1.9750. Min Act: -0.0001
Data Index: 1442771 (Python Code)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8492. Min Range: -2.8492
Max Act: 1.7098. Min Act: -0.0001
Data Index: 1629927 (Python Code)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8492. Min Range: -2.8492
Max Act: 1.5728. Min Act: -0.0001
Data Index: 1628479 (Python Code)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8492. Min Range: -2.8492
Max Act: 1.8356. Min Act: -0.0001
Data Index: 1551896 (Python Code)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8492. Min Range: -2.8492
Max Act: 1.8010. Min Act: -0.0001
Data Index: 1558248 (Python Code)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8492. Min Range: -2.8492
Max Act: 1.7787. Min Act: -0.0001
Data Index: 1562864 (Python Code)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8492. Min Range: -2.8492
Max Act: 1.5116. Min Act: -0.0001
Data Index: 1626702 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8492. Min Range: -2.8492
Max Act: 1.6452. Min Act: -0.0001
Data Index: 1648126 (Python Code)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8492. Min Range: -2.8492
Max Act: 1.6579. Min Act: -0.0001
Data Index: 1365729 (Python Code)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19