Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2678 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.3571. Min Range: -1.3571
Max Act: 1.3571. Min Act: -0.0001
Data Index: 1442241 (Python Code)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3571. Min Range: -1.3571
Max Act: 1.2658. Min Act: -0.0001
Data Index: 1362118 (Python Code)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3571. Min Range: -1.3571
Max Act: 1.2060. Min Act: -0.0001
Data Index: 124768 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3571. Min Range: -1.3571
Max Act: 1.1445. Min Act: -0.0001
Data Index: 1442769 (Python Code)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3571. Min Range: -1.3571
Max Act: 1.3352. Min Act: -0.0001
Data Index: 1446906 (Python Code)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3571. Min Range: -1.3571
Max Act: 1.2330. Min Act: -0.0001
Data Index: 546096 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3571. Min Range: -1.3571
Max Act: 1.2678. Min Act: -0.0001
Data Index: 1578234 (Python Code)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3571. Min Range: -1.3571
Max Act: 1.2791. Min Act: -0.0001
Data Index: 1590090 (Python Code)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3571. Min Range: -1.3571
Max Act: 1.1541. Min Act: -0.0001
Data Index: 927553 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3571. Min Range: -1.3571
Max Act: 1.2773. Min Act: -0.0001
Data Index: 1391529 (Python Code)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3571. Min Range: -1.3571
Max Act: 1.2478. Min Act: -0.0001
Data Index: 1207543 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3571. Min Range: -1.3571
Max Act: 1.2117. Min Act: -0.0001
Data Index: 1430932 (Python Code)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3571. Min Range: -1.3571
Max Act: 1.1860. Min Act: -0.0001
Data Index: 1406153 (Python Code)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3571. Min Range: -1.3571
Max Act: 1.2244. Min Act: -0.0001
Data Index: 1609406 (Python Code)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3571. Min Range: -1.3571
Max Act: 1.1723. Min Act: -0.0001
Data Index: 1573347 (Python Code)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3571. Min Range: -1.3571
Max Act: 1.1306. Min Act: -0.0001
Data Index: 1625132 (Python Code)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3571. Min Range: -1.3571
Max Act: 1.1531. Min Act: -0.0001
Data Index: 1640949 (Python Code)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3571. Min Range: -1.3571
Max Act: 1.0975. Min Act: -0.0001
Data Index: 1170665 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3571. Min Range: -1.3571
Max Act: 1.2500. Min Act: -0.0001
Data Index: 1365070 (Python Code)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3571. Min Range: -1.3571
Max Act: 1.0124. Min Act: -0.0001
Data Index: 783436 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19