Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2775 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 4.5359. Min Range: -4.5359
Max Act: 4.5359. Min Act: -0.0001
Data Index: 671727 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5359. Min Range: -4.5359
Max Act: 3.7574. Min Act: -0.0001
Data Index: 603628 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5359. Min Range: -4.5359
Max Act: 3.1628. Min Act: -0.0001
Data Index: 700197 (C4 (Web Text))
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5359. Min Range: -4.5359
Max Act: 3.2525. Min Act: -0.0001
Data Index: 1100444 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5359. Min Range: -4.5359
Max Act: 3.2034. Min Act: -0.0001
Data Index: 1202874 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5359. Min Range: -4.5359
Max Act: 2.9046. Min Act: -0.0000
Data Index: 593838 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5359. Min Range: -4.5359
Max Act: 2.7245. Min Act: -0.0000
Data Index: 874475 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5359. Min Range: -4.5359
Max Act: 2.7589. Min Act: -0.0001
Data Index: 832705 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5359. Min Range: -4.5359
Max Act: 3.2071. Min Act: -0.0001
Data Index: 360685 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5359. Min Range: -4.5359
Max Act: 2.9349. Min Act: -0.0001
Data Index: 243825 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5359. Min Range: -4.5359
Max Act: 2.9663. Min Act: -0.0001
Data Index: 612324 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5359. Min Range: -4.5359
Max Act: 2.6928. Min Act: -0.0001
Data Index: 762859 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5359. Min Range: -4.5359
Max Act: 2.2146. Min Act: -0.0000
Data Index: 79994 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5359. Min Range: -4.5359
Max Act: 2.3178. Min Act: -0.0001
Data Index: 604029 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5359. Min Range: -4.5359
Max Act: 2.6084. Min Act: -0.0001
Data Index: 1134374 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5359. Min Range: -4.5359
Max Act: 2.1957. Min Act: -0.0000
Data Index: 1170848 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5359. Min Range: -4.5359
Max Act: 2.5459. Min Act: -0.0001
Data Index: 725871 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5359. Min Range: -4.5359
Max Act: 2.4149. Min Act: -0.0001
Data Index: 555226 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5359. Min Range: -4.5359
Max Act: 2.4742. Min Act: -0.0001
Data Index: 1633326 (Python Code)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5359. Min Range: -4.5359
Max Act: 2.4734. Min Act: -0.0001
Data Index: 863016 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19