Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3564 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 4.4696. Min Range: -4.4696
Max Act: 4.4696. Min Act: -0.0001
Data Index: 1239929 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4696. Min Range: -4.4696
Max Act: 4.0448. Min Act: -0.0001
Data Index: 884087 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4696. Min Range: -4.4696
Max Act: 4.0952. Min Act: -0.0001
Data Index: 561697 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4696. Min Range: -4.4696
Max Act: 4.2276. Min Act: -0.0001
Data Index: 757595 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4696. Min Range: -4.4696
Max Act: 3.9680. Min Act: -0.0001
Data Index: 1295621 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4696. Min Range: -4.4696
Max Act: 4.1095. Min Act: -0.0001
Data Index: 328222 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4696. Min Range: -4.4696
Max Act: 4.0958. Min Act: -0.0001
Data Index: 468162 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4696. Min Range: -4.4696
Max Act: 4.1014. Min Act: -0.0001
Data Index: 423539 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4696. Min Range: -4.4696
Max Act: 4.0924. Min Act: -0.0001
Data Index: 528755 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4696. Min Range: -4.4696
Max Act: 3.9112. Min Act: -0.0001
Data Index: 889032 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4696. Min Range: -4.4696
Max Act: 4.0227. Min Act: -0.0001
Data Index: 590791 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4696. Min Range: -4.4696
Max Act: 3.9828. Min Act: -0.0001
Data Index: 77918 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4696. Min Range: -4.4696
Max Act: 4.0033. Min Act: -0.0001
Data Index: 350821 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4696. Min Range: -4.4696
Max Act: 3.9782. Min Act: -0.0001
Data Index: 746187 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4696. Min Range: -4.4696
Max Act: 3.9820. Min Act: -0.0001
Data Index: 212505 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4696. Min Range: -4.4696
Max Act: 4.1448. Min Act: -0.0001
Data Index: 140596 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4696. Min Range: -4.4696
Max Act: 3.9415. Min Act: -0.0001
Data Index: 1054811 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4696. Min Range: -4.4696
Max Act: 3.9201. Min Act: -0.0001
Data Index: 1274694 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4696. Min Range: -4.4696
Max Act: 3.8999. Min Act: -0.0001
Data Index: 1158409 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4696. Min Range: -4.4696
Max Act: 3.8712. Min Act: -0.0001
Data Index: 846493 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19