Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2618 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.5798. Min Range: -0.5798
Max Act: 0.5760. Min Act: -0.0001
Data Index: 572451 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5798. Min Range: -0.5798
Max Act: 0.5758. Min Act: -0.0001
Data Index: 1084303 (C4 (Web Text))
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5798. Min Range: -0.5798
Max Act: 0.5431. Min Act: -0.0001
Data Index: 1394760 (Python Code)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5798. Min Range: -0.5798
Max Act: 0.5158. Min Act: -0.0001
Data Index: 304277 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5798. Min Range: -0.5798
Max Act: 0.4700. Min Act: -0.0001
Data Index: 161559 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5798. Min Range: -0.5798
Max Act: 0.5254. Min Act: -0.0001
Data Index: 302613 (C4 (Web Text))
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5798. Min Range: -0.5798
Max Act: 0.4888. Min Act: -0.0001
Data Index: 569107 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5798. Min Range: -0.5798
Max Act: 0.5798. Min Act: -0.0001
Data Index: 568470 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5798. Min Range: -0.5798
Max Act: 0.5017. Min Act: -0.0001
Data Index: 553015 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5798. Min Range: -0.5798
Max Act: 0.4611. Min Act: -0.0001
Data Index: 302300 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5798. Min Range: -0.5798
Max Act: 0.4713. Min Act: -0.0001
Data Index: 1494756 (Python Code)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5798. Min Range: -0.5798
Max Act: 0.4398. Min Act: -0.0001
Data Index: 1591569 (Python Code)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5798. Min Range: -0.5798
Max Act: 0.4065. Min Act: -0.0001
Data Index: 485473 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5798. Min Range: -0.5798
Max Act: 0.4660. Min Act: -0.0001
Data Index: 1029505 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5798. Min Range: -0.5798
Max Act: 0.4771. Min Act: -0.0001
Data Index: 1575104 (Python Code)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5798. Min Range: -0.5798
Max Act: 0.4767. Min Act: -0.0001
Data Index: 384145 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5798. Min Range: -0.5798
Max Act: 0.4402. Min Act: -0.0001
Data Index: 1635083 (Python Code)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5798. Min Range: -0.5798
Max Act: 0.4480. Min Act: -0.0001
Data Index: 1369993 (Python Code)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5798. Min Range: -0.5798
Max Act: 0.4554. Min Act: -0.0001
Data Index: 1485537 (Python Code)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5798. Min Range: -0.5798
Max Act: 0.4558. Min Act: -0.0001
Data Index: 948629 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19