Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 556 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.5872. Min Range: -1.5872
Max Act: 1.5872. Min Act: -0.0001
Data Index: 1533993 (Python Code)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5872. Min Range: -1.5872
Max Act: 1.4499. Min Act: -0.0001
Data Index: 1654975 (Python Code)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5872. Min Range: -1.5872
Max Act: 1.5008. Min Act: -0.0001
Data Index: 1527192 (Python Code)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5872. Min Range: -1.5872
Max Act: 1.4814. Min Act: -0.0001
Data Index: 1557430 (Python Code)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5872. Min Range: -1.5872
Max Act: 1.4226. Min Act: -0.0001
Data Index: 1517847 (Python Code)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5872. Min Range: -1.5872
Max Act: 1.4131. Min Act: -0.0001
Data Index: 1458538 (Python Code)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5872. Min Range: -1.5872
Max Act: 1.4409. Min Act: -0.0001
Data Index: 1656406 (Python Code)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5872. Min Range: -1.5872
Max Act: 1.4307. Min Act: -0.0001
Data Index: 1527576 (Python Code)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5872. Min Range: -1.5872
Max Act: 1.4396. Min Act: -0.0001
Data Index: 1650118 (Python Code)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5872. Min Range: -1.5872
Max Act: 1.3139. Min Act: -0.0001
Data Index: 1383381 (Python Code)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5872. Min Range: -1.5872
Max Act: 1.3780. Min Act: -0.0001
Data Index: 1456377 (Python Code)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5872. Min Range: -1.5872
Max Act: 1.3802. Min Act: -0.0001
Data Index: 1546506 (Python Code)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5872. Min Range: -1.5872
Max Act: 1.3698. Min Act: -0.0001
Data Index: 1519534 (Python Code)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5872. Min Range: -1.5872
Max Act: 1.3990. Min Act: -0.0001
Data Index: 1517478 (Python Code)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5872. Min Range: -1.5872
Max Act: 1.2589. Min Act: -0.0001
Data Index: 1455663 (Python Code)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5872. Min Range: -1.5872
Max Act: 1.4047. Min Act: -0.0001
Data Index: 1620229 (Python Code)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5872. Min Range: -1.5872
Max Act: 1.3153. Min Act: -0.0001
Data Index: 1628731 (Python Code)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5872. Min Range: -1.5872
Max Act: 1.3698. Min Act: -0.0001
Data Index: 1521273 (Python Code)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5872. Min Range: -1.5872
Max Act: 1.2507. Min Act: -0.0001
Data Index: 1511888 (Python Code)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5872. Min Range: -1.5872
Max Act: 1.2737. Min Act: -0.0001
Data Index: 1410012 (Python Code)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19