Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1704 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.9594. Min Range: -1.9594
Max Act: 1.9594. Min Act: -0.0001
Data Index: 1527097 (Python Code)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9594. Min Range: -1.9594
Max Act: 1.9206. Min Act: -0.0001
Data Index: 1386314 (Python Code)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9594. Min Range: -1.9594
Max Act: 1.6434. Min Act: -0.0001
Data Index: 1428788 (Python Code)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9594. Min Range: -1.9594
Max Act: 1.6794. Min Act: -0.0001
Data Index: 1548551 (Python Code)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9594. Min Range: -1.9594
Max Act: 1.7171. Min Act: -0.0001
Data Index: 1446441 (Python Code)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9594. Min Range: -1.9594
Max Act: 1.6545. Min Act: -0.0001
Data Index: 1488347 (Python Code)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9594. Min Range: -1.9594
Max Act: 1.5877. Min Act: -0.0001
Data Index: 1524447 (Python Code)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9594. Min Range: -1.9594
Max Act: 1.6615. Min Act: -0.0001
Data Index: 1482763 (Python Code)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9594. Min Range: -1.9594
Max Act: 1.6550. Min Act: -0.0001
Data Index: 1568560 (Python Code)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9594. Min Range: -1.9594
Max Act: 1.6368. Min Act: -0.0001
Data Index: 1361979 (Python Code)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9594. Min Range: -1.9594
Max Act: 1.6869. Min Act: -0.0001
Data Index: 1545214 (Python Code)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9594. Min Range: -1.9594
Max Act: 1.7067. Min Act: -0.0001
Data Index: 1482419 (Python Code)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9594. Min Range: -1.9594
Max Act: 1.5651. Min Act: -0.0001
Data Index: 1598889 (Python Code)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9594. Min Range: -1.9594
Max Act: 1.6043. Min Act: -0.0001
Data Index: 1645057 (Python Code)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9594. Min Range: -1.9594
Max Act: 1.5947. Min Act: -0.0001
Data Index: 1436539 (Python Code)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9594. Min Range: -1.9594
Max Act: 1.5005. Min Act: -0.0001
Data Index: 1589451 (Python Code)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9594. Min Range: -1.9594
Max Act: 1.5923. Min Act: -0.0001
Data Index: 1446091 (Python Code)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9594. Min Range: -1.9594
Max Act: 1.5705. Min Act: -0.0001
Data Index: 1526359 (Python Code)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9594. Min Range: -1.9594
Max Act: 1.5327. Min Act: -0.0001
Data Index: 1392078 (Python Code)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9594. Min Range: -1.9594
Max Act: 1.5325. Min Act: -0.0001
Data Index: 1616682 (Python Code)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19