Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3238 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.2246. Min Range: -0.2246
Max Act: 0.2246. Min Act: -0.0001
Data Index: 1566431 (Python Code)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2246. Min Range: -0.2246
Max Act: 0.1879. Min Act: -0.0001
Data Index: 707604 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2246. Min Range: -0.2246
Max Act: 0.1831. Min Act: -0.0001
Data Index: 800486 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2246. Min Range: -0.2246
Max Act: 0.1634. Min Act: -0.0001
Data Index: 1626659 (Python Code)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2246. Min Range: -0.2246
Max Act: 0.1842. Min Act: -0.0001
Data Index: 1584994 (Python Code)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2246. Min Range: -0.2246
Max Act: 0.1878. Min Act: -0.0001
Data Index: 1450605 (Python Code)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2246. Min Range: -0.2246
Max Act: 0.1646. Min Act: -0.0001
Data Index: 1538380 (Python Code)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2246. Min Range: -0.2246
Max Act: 0.1653. Min Act: -0.0001
Data Index: 1442506 (Python Code)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2246. Min Range: -0.2246
Max Act: 0.1695. Min Act: -0.0001
Data Index: 1643693 (Python Code)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2246. Min Range: -0.2246
Max Act: 0.1638. Min Act: -0.0001
Data Index: 939622 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2246. Min Range: -0.2246
Max Act: 0.1698. Min Act: -0.0001
Data Index: 1127958 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2246. Min Range: -0.2246
Max Act: 0.1491. Min Act: -0.0001
Data Index: 1410393 (Python Code)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2246. Min Range: -0.2246
Max Act: 0.1660. Min Act: -0.0001
Data Index: 1515176 (Python Code)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2246. Min Range: -0.2246
Max Act: 0.1546. Min Act: -0.0001
Data Index: 259061 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2246. Min Range: -0.2246
Max Act: 0.1439. Min Act: -0.0001
Data Index: 1486647 (Python Code)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2246. Min Range: -0.2246
Max Act: 0.1475. Min Act: -0.0001
Data Index: 1477689 (Python Code)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2246. Min Range: -0.2246
Max Act: 0.1524. Min Act: -0.0001
Data Index: 1362624 (Python Code)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2246. Min Range: -0.2246
Max Act: 0.1509. Min Act: -0.0001
Data Index: 1501435 (Python Code)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2246. Min Range: -0.2246
Max Act: 0.1510. Min Act: -0.0001
Data Index: 62711 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2246. Min Range: -0.2246
Max Act: 0.1491. Min Act: -0.0001
Data Index: 1398047 (Python Code)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19