Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3437 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 4.0080. Min Range: -4.0080
Max Act: 4.0080. Min Act: -0.0001
Data Index: 1530882 (Python Code)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0080. Min Range: -4.0080
Max Act: 2.8770. Min Act: -0.0001
Data Index: 1392264 (Python Code)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0080. Min Range: -4.0080
Max Act: 2.8578. Min Act: -0.0001
Data Index: 1491037 (Python Code)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0080. Min Range: -4.0080
Max Act: 2.3209. Min Act: -0.0001
Data Index: 1581887 (Python Code)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0080. Min Range: -4.0080
Max Act: 2.0997. Min Act: -0.0001
Data Index: 597413 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0080. Min Range: -4.0080
Max Act: 2.3626. Min Act: -0.0001
Data Index: 1082043 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0080. Min Range: -4.0080
Max Act: 2.1374. Min Act: -0.0001
Data Index: 562049 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0080. Min Range: -4.0080
Max Act: 1.6738. Min Act: -0.0001
Data Index: 1374368 (Python Code)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0080. Min Range: -4.0080
Max Act: 2.1896. Min Act: -0.0001
Data Index: 736718 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0080. Min Range: -4.0080
Max Act: 1.4967. Min Act: -0.0001
Data Index: 1641062 (Python Code)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0080. Min Range: -4.0080
Max Act: 1.4409. Min Act: -0.0001
Data Index: 1526323 (Python Code)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0080. Min Range: -4.0080
Max Act: 1.9592. Min Act: -0.0001
Data Index: 1420614 (Python Code)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0080. Min Range: -4.0080
Max Act: 1.8900. Min Act: -0.0001
Data Index: 225120 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0080. Min Range: -4.0080
Max Act: 2.5148. Min Act: -0.0001
Data Index: 730773 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0080. Min Range: -4.0080
Max Act: 1.7481. Min Act: -0.0001
Data Index: 545626 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0080. Min Range: -4.0080
Max Act: 2.0221. Min Act: -0.0001
Data Index: 1370206 (Python Code)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0080. Min Range: -4.0080
Max Act: 1.8011. Min Act: -0.0001
Data Index: 616924 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0080. Min Range: -4.0080
Max Act: 2.0058. Min Act: -0.0001
Data Index: 1418848 (Python Code)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0080. Min Range: -4.0080
Max Act: 1.8496. Min Act: -0.0001
Data Index: 890636 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0080. Min Range: -4.0080
Max Act: 1.9410. Min Act: -0.0001
Data Index: 855867 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19