Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4611 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.3928. Min Range: -1.3928
Max Act: 1.3928. Min Act: -0.0001
Data Index: 552563 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3928. Min Range: -1.3928
Max Act: 1.2541. Min Act: -0.0001
Data Index: 441205 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3928. Min Range: -1.3928
Max Act: 1.3521. Min Act: -0.0001
Data Index: 446122 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3928. Min Range: -1.3928
Max Act: 1.2118. Min Act: -0.0001
Data Index: 50685 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3928. Min Range: -1.3928
Max Act: 1.1202. Min Act: -0.0001
Data Index: 608071 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3928. Min Range: -1.3928
Max Act: 1.1630. Min Act: -0.0001
Data Index: 490272 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3928. Min Range: -1.3928
Max Act: 1.1056. Min Act: -0.0001
Data Index: 533900 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3928. Min Range: -1.3928
Max Act: 1.2042. Min Act: -0.0001
Data Index: 1223523 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3928. Min Range: -1.3928
Max Act: 1.0359. Min Act: -0.0001
Data Index: 467257 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3928. Min Range: -1.3928
Max Act: 1.1328. Min Act: -0.0001
Data Index: 714428 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3928. Min Range: -1.3928
Max Act: 1.1067. Min Act: -0.0001
Data Index: 719908 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3928. Min Range: -1.3928
Max Act: 0.9984. Min Act: -0.0001
Data Index: 281668 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3928. Min Range: -1.3928
Max Act: 1.0403. Min Act: -0.0001
Data Index: 1314908 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3928. Min Range: -1.3928
Max Act: 1.0343. Min Act: -0.0001
Data Index: 1269398 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3928. Min Range: -1.3928
Max Act: 1.0982. Min Act: -0.0001
Data Index: 1281181 (C4 (Web Text))
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3928. Min Range: -1.3928
Max Act: 0.9762. Min Act: -0.0001
Data Index: 356295 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3928. Min Range: -1.3928
Max Act: 1.0526. Min Act: -0.0001
Data Index: 78434 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3928. Min Range: -1.3928
Max Act: 1.1076. Min Act: -0.0001
Data Index: 228713 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3928. Min Range: -1.3928
Max Act: 1.0388. Min Act: -0.0001
Data Index: 797707 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3928. Min Range: -1.3928
Max Act: 0.9646. Min Act: -0.0001
Data Index: 720439 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19