Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3012 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.0886. Min Range: -0.0886
Max Act: 0.0886. Min Act: -0.0001
Data Index: 1498925 (Python Code)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0886. Min Range: -0.0886
Max Act: 0.0708. Min Act: -0.0001
Data Index: 870833 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0886. Min Range: -0.0886
Max Act: 0.0799. Min Act: -0.0001
Data Index: 408455 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0886. Min Range: -0.0886
Max Act: 0.0734. Min Act: -0.0001
Data Index: 556849 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0886. Min Range: -0.0886
Max Act: 0.0687. Min Act: -0.0001
Data Index: 783804 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0886. Min Range: -0.0886
Max Act: 0.0644. Min Act: -0.0001
Data Index: 1442539 (Python Code)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0886. Min Range: -0.0886
Max Act: 0.0659. Min Act: -0.0001
Data Index: 1401556 (Python Code)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0886. Min Range: -0.0886
Max Act: 0.0653. Min Act: -0.0001
Data Index: 107085 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0886. Min Range: -0.0886
Max Act: 0.0547. Min Act: -0.0001
Data Index: 1264426 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0886. Min Range: -0.0886
Max Act: 0.0587. Min Act: -0.0001
Data Index: 1383477 (Python Code)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0886. Min Range: -0.0886
Max Act: 0.0559. Min Act: -0.0001
Data Index: 521287 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0886. Min Range: -0.0886
Max Act: 0.0559. Min Act: -0.0001
Data Index: 1353310 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0886. Min Range: -0.0886
Max Act: 0.0516. Min Act: -0.0001
Data Index: 797940 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0886. Min Range: -0.0886
Max Act: 0.0510. Min Act: -0.0001
Data Index: 1491157 (Python Code)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0886. Min Range: -0.0886
Max Act: 0.0508. Min Act: -0.0001
Data Index: 687596 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0886. Min Range: -0.0886
Max Act: 0.0525. Min Act: -0.0001
Data Index: 1603193 (Python Code)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0886. Min Range: -0.0886
Max Act: 0.0527. Min Act: -0.0001
Data Index: 281756 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0886. Min Range: -0.0886
Max Act: 0.0552. Min Act: -0.0001
Data Index: 1489080 (Python Code)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0886. Min Range: -0.0886
Max Act: 0.0577. Min Act: -0.0001
Data Index: 1359998 (Python Code)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0886. Min Range: -0.0886
Max Act: 0.0500. Min Act: -0.0001
Data Index: 1644233 (Python Code)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19