Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4401 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.0966. Min Range: -0.0966
Max Act: 0.0966. Min Act: -0.0001
Data Index: 951781 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0966. Min Range: -0.0966
Max Act: 0.0769. Min Act: -0.0001
Data Index: 1354580 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0966. Min Range: -0.0966
Max Act: 0.0677. Min Act: -0.0001
Data Index: 1452017 (Python Code)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0966. Min Range: -0.0966
Max Act: 0.0704. Min Act: -0.0001
Data Index: 1435834 (Python Code)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0966. Min Range: -0.0966
Max Act: 0.0660. Min Act: -0.0001
Data Index: 1355455 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0966. Min Range: -0.0966
Max Act: 0.0660. Min Act: -0.0001
Data Index: 281417 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0966. Min Range: -0.0966
Max Act: 0.0641. Min Act: -0.0001
Data Index: 1191699 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0966. Min Range: -0.0966
Max Act: 0.0586. Min Act: -0.0001
Data Index: 622830 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0966. Min Range: -0.0966
Max Act: 0.0571. Min Act: -0.0001
Data Index: 847929 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0966. Min Range: -0.0966
Max Act: 0.0605. Min Act: -0.0001
Data Index: 408896 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0966. Min Range: -0.0966
Max Act: 0.0528. Min Act: -0.0001
Data Index: 201988 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0966. Min Range: -0.0966
Max Act: 0.0559. Min Act: -0.0001
Data Index: 859161 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0966. Min Range: -0.0966
Max Act: 0.0585. Min Act: -0.0001
Data Index: 930682 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0966. Min Range: -0.0966
Max Act: 0.0560. Min Act: -0.0001
Data Index: 374545 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0966. Min Range: -0.0966
Max Act: 0.0566. Min Act: -0.0001
Data Index: 639733 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0966. Min Range: -0.0966
Max Act: 0.0544. Min Act: -0.0001
Data Index: 1327454 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0966. Min Range: -0.0966
Max Act: 0.0535. Min Act: -0.0001
Data Index: 960938 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0966. Min Range: -0.0966
Max Act: 0.0537. Min Act: -0.0001
Data Index: 1474357 (Python Code)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0966. Min Range: -0.0966
Max Act: 0.0507. Min Act: -0.0001
Data Index: 1003772 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0966. Min Range: -0.0966
Max Act: 0.0516. Min Act: -0.0001
Data Index: 640210 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19