Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3166 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.5799. Min Range: -3.5799
Max Act: 3.5097. Min Act: -0.0001
Data Index: 1618879 (Python Code)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5799. Min Range: -3.5799
Max Act: 3.4771. Min Act: -0.0001
Data Index: 1571445 (Python Code)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5799. Min Range: -3.5799
Max Act: 3.5799. Min Act: -0.0001
Data Index: 1528169 (Python Code)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5799. Min Range: -3.5799
Max Act: 2.9667. Min Act: -0.0001
Data Index: 1415374 (Python Code)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5799. Min Range: -3.5799
Max Act: 2.9550. Min Act: -0.0001
Data Index: 1475108 (Python Code)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5799. Min Range: -3.5799
Max Act: 2.8479. Min Act: -0.0001
Data Index: 1571014 (Python Code)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5799. Min Range: -3.5799
Max Act: 3.0436. Min Act: -0.0001
Data Index: 1376187 (Python Code)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5799. Min Range: -3.5799
Max Act: 2.9198. Min Act: -0.0001
Data Index: 1556916 (Python Code)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5799. Min Range: -3.5799
Max Act: 2.7831. Min Act: -0.0001
Data Index: 1476055 (Python Code)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5799. Min Range: -3.5799
Max Act: 2.8642. Min Act: -0.0001
Data Index: 1382402 (Python Code)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5799. Min Range: -3.5799
Max Act: 2.7659. Min Act: -0.0001
Data Index: 1385231 (Python Code)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5799. Min Range: -3.5799
Max Act: 2.7452. Min Act: -0.0001
Data Index: 1447240 (Python Code)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5799. Min Range: -3.5799
Max Act: 2.7402. Min Act: -0.0001
Data Index: 1415619 (Python Code)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5799. Min Range: -3.5799
Max Act: 2.5739. Min Act: -0.0001
Data Index: 1503764 (Python Code)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5799. Min Range: -3.5799
Max Act: 2.4485. Min Act: -0.0001
Data Index: 1468594 (Python Code)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5799. Min Range: -3.5799
Max Act: 2.4404. Min Act: -0.0001
Data Index: 1594833 (Python Code)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5799. Min Range: -3.5799
Max Act: 2.3986. Min Act: -0.0001
Data Index: 1445833 (Python Code)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5799. Min Range: -3.5799
Max Act: 2.4663. Min Act: -0.0001
Data Index: 1395614 (Python Code)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5799. Min Range: -3.5799
Max Act: 2.3856. Min Act: -0.0001
Data Index: 1433997 (Python Code)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5799. Min Range: -3.5799
Max Act: 2.3060. Min Act: -0.0001
Data Index: 1503176 (Python Code)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19