Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3780 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.2034. Min Range: -1.2034
Max Act: 1.2034. Min Act: -0.0001
Data Index: 131396 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2034. Min Range: -1.2034
Max Act: 1.1141. Min Act: -0.0001
Data Index: 469581 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2034. Min Range: -1.2034
Max Act: 0.9399. Min Act: -0.0001
Data Index: 210918 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2034. Min Range: -1.2034
Max Act: 0.9679. Min Act: -0.0001
Data Index: 743334 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2034. Min Range: -1.2034
Max Act: 0.9339. Min Act: -0.0001
Data Index: 770676 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2034. Min Range: -1.2034
Max Act: 0.9159. Min Act: -0.0001
Data Index: 501557 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2034. Min Range: -1.2034
Max Act: 0.8760. Min Act: -0.0001
Data Index: 913927 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2034. Min Range: -1.2034
Max Act: 0.9015. Min Act: -0.0001
Data Index: 801935 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2034. Min Range: -1.2034
Max Act: 0.8608. Min Act: -0.0001
Data Index: 773649 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2034. Min Range: -1.2034
Max Act: 0.8865. Min Act: -0.0001
Data Index: 92547 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2034. Min Range: -1.2034
Max Act: 0.8981. Min Act: -0.0001
Data Index: 191338 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2034. Min Range: -1.2034
Max Act: 0.8858. Min Act: -0.0001
Data Index: 1625737 (Python Code)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2034. Min Range: -1.2034
Max Act: 0.9204. Min Act: -0.0001
Data Index: 1083293 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2034. Min Range: -1.2034
Max Act: 0.8784. Min Act: -0.0001
Data Index: 1584893 (Python Code)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2034. Min Range: -1.2034
Max Act: 0.8507. Min Act: -0.0001
Data Index: 1163243 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2034. Min Range: -1.2034
Max Act: 0.8574. Min Act: -0.0001
Data Index: 1210657 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2034. Min Range: -1.2034
Max Act: 0.8821. Min Act: -0.0001
Data Index: 1302497 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2034. Min Range: -1.2034
Max Act: 0.8225. Min Act: -0.0001
Data Index: 462042 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2034. Min Range: -1.2034
Max Act: 0.8214. Min Act: -0.0001
Data Index: 705144 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2034. Min Range: -1.2034
Max Act: 0.8470. Min Act: -0.0001
Data Index: 674449 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19