Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5327 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.2018. Min Range: -0.2018
Max Act: 0.2018. Min Act: -0.0002
Data Index: 928366 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 0.2018. Min Range: -0.2018
Max Act: 0.1895. Min Act: -0.0002
Data Index: 355577 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 0.2018. Min Range: -0.2018
Max Act: 0.1953. Min Act: -0.0002
Data Index: 627157 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 0.2018. Min Range: -0.2018
Max Act: 0.1863. Min Act: -0.0002
Data Index: 169338 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 0.2018. Min Range: -0.2018
Max Act: 0.1898. Min Act: -0.0002
Data Index: 479362 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 0.2018. Min Range: -0.2018
Max Act: 0.1888. Min Act: -0.0002
Data Index: 5320 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 0.2018. Min Range: -0.2018
Max Act: 0.1874. Min Act: -0.0002
Data Index: 1310278 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 0.2018. Min Range: -0.2018
Max Act: 0.1767. Min Act: -0.0002
Data Index: 1201833 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 0.2018. Min Range: -0.2018
Max Act: 0.1776. Min Act: -0.0002
Data Index: 1018346 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 0.2018. Min Range: -0.2018
Max Act: 0.1761. Min Act: -0.0002
Data Index: 382896 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 0.2018. Min Range: -0.2018
Max Act: 0.1741. Min Act: -0.0002
Data Index: 222237 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 0.2018. Min Range: -0.2018
Max Act: 0.1798. Min Act: -0.0002
Data Index: 451856 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 0.2018. Min Range: -0.2018
Max Act: 0.1737. Min Act: -0.0002
Data Index: 1263981 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 0.2018. Min Range: -0.2018
Max Act: 0.1751. Min Act: -0.0002
Data Index: 635284 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 0.2018. Min Range: -0.2018
Max Act: 0.1734. Min Act: -0.0002
Data Index: 919003 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 0.2018. Min Range: -0.2018
Max Act: 0.1720. Min Act: -0.0002
Data Index: 1019318 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 0.2018. Min Range: -0.2018
Max Act: 0.1786. Min Act: -0.0002
Data Index: 810075 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 0.2018. Min Range: -0.2018
Max Act: 0.1713. Min Act: -0.0002
Data Index: 1258227 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 0.2018. Min Range: -0.2018
Max Act: 0.1715. Min Act: -0.0002
Data Index: 689376 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 0.2018. Min Range: -0.2018
Max Act: 0.1638. Min Act: -0.0002
Data Index: 369364 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full textTruncated
Full Text #19