Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3697 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.6991. Min Range: -0.6991
Max Act: 0.6991. Min Act: -0.0001
Data Index: 1604712 (Python Code)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6991. Min Range: -0.6991
Max Act: 0.6006. Min Act: -0.0001
Data Index: 276045 (C4 (Web Text))
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6991. Min Range: -0.6991
Max Act: 0.6620. Min Act: -0.0001
Data Index: 1396159 (Python Code)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6991. Min Range: -0.6991
Max Act: 0.6442. Min Act: -0.0001
Data Index: 1484946 (Python Code)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6991. Min Range: -0.6991
Max Act: 0.5919. Min Act: -0.0001
Data Index: 1431421 (Python Code)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6991. Min Range: -0.6991
Max Act: 0.4675. Min Act: -0.0001
Data Index: 129639 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6991. Min Range: -0.6991
Max Act: 0.6051. Min Act: -0.0001
Data Index: 1604556 (Python Code)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6991. Min Range: -0.6991
Max Act: 0.5234. Min Act: -0.0001
Data Index: 876518 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6991. Min Range: -0.6991
Max Act: 0.5620. Min Act: -0.0001
Data Index: 1417710 (Python Code)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6991. Min Range: -0.6991
Max Act: 0.5252. Min Act: -0.0001
Data Index: 791652 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6991. Min Range: -0.6991
Max Act: 0.5090. Min Act: -0.0001
Data Index: 1408470 (Python Code)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6991. Min Range: -0.6991
Max Act: 0.5736. Min Act: -0.0001
Data Index: 1514414 (Python Code)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6991. Min Range: -0.6991
Max Act: 0.5677. Min Act: -0.0001
Data Index: 1394209 (Python Code)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6991. Min Range: -0.6991
Max Act: 0.5300. Min Act: -0.0001
Data Index: 1534154 (Python Code)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6991. Min Range: -0.6991
Max Act: 0.5164. Min Act: -0.0001
Data Index: 1035221 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6991. Min Range: -0.6991
Max Act: 0.5323. Min Act: -0.0001
Data Index: 470494 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6991. Min Range: -0.6991
Max Act: 0.5414. Min Act: -0.0001
Data Index: 1393501 (Python Code)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6991. Min Range: -0.6991
Max Act: 0.5219. Min Act: -0.0001
Data Index: 1572055 (Python Code)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6991. Min Range: -0.6991
Max Act: 0.4543. Min Act: -0.0001
Data Index: 920062 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6991. Min Range: -0.6991
Max Act: 0.5169. Min Act: -0.0001
Data Index: 493597 (C4 (Web Text))
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19