Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5089 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.7834. Min Range: -0.7834
Max Act: 0.7819. Min Act: -0.0001
Data Index: 1075092 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7834. Min Range: -0.7834
Max Act: 0.7834. Min Act: -0.0001
Data Index: 1264789 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7834. Min Range: -0.7834
Max Act: 0.7363. Min Act: -0.0001
Data Index: 1409598 (Python Code)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7834. Min Range: -0.7834
Max Act: 0.6999. Min Act: -0.0001
Data Index: 1433125 (Python Code)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7834. Min Range: -0.7834
Max Act: 0.7553. Min Act: -0.0001
Data Index: 1261792 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7834. Min Range: -0.7834
Max Act: 0.7421. Min Act: -0.0001
Data Index: 1406904 (Python Code)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7834. Min Range: -0.7834
Max Act: 0.7585. Min Act: -0.0001
Data Index: 633714 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7834. Min Range: -0.7834
Max Act: 0.6559. Min Act: -0.0001
Data Index: 1458239 (Python Code)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7834. Min Range: -0.7834
Max Act: 0.7108. Min Act: -0.0001
Data Index: 1538629 (Python Code)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7834. Min Range: -0.7834
Max Act: 0.6863. Min Act: -0.0001
Data Index: 883584 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7834. Min Range: -0.7834
Max Act: 0.6701. Min Act: -0.0001
Data Index: 1066449 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7834. Min Range: -0.7834
Max Act: 0.6702. Min Act: -0.0001
Data Index: 1603572 (Python Code)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7834. Min Range: -0.7834
Max Act: 0.6523. Min Act: -0.0001
Data Index: 729916 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7834. Min Range: -0.7834
Max Act: 0.6494. Min Act: -0.0001
Data Index: 1371722 (Python Code)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7834. Min Range: -0.7834
Max Act: 0.6751. Min Act: -0.0001
Data Index: 1397418 (Python Code)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7834. Min Range: -0.7834
Max Act: 0.6603. Min Act: -0.0001
Data Index: 1627709 (Python Code)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7834. Min Range: -0.7834
Max Act: 0.5491. Min Act: -0.0001
Data Index: 1441256 (Python Code)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7834. Min Range: -0.7834
Max Act: 0.6301. Min Act: -0.0001
Data Index: 646873 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7834. Min Range: -0.7834
Max Act: 0.6514. Min Act: -0.0001
Data Index: 746020 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7834. Min Range: -0.7834
Max Act: 0.6248. Min Act: -0.0001
Data Index: 1387542 (Python Code)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19