Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3427 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 4.8423. Min Range: -4.8423
Max Act: 4.8423. Min Act: -0.0002
Data Index: 669701 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8423. Min Range: -4.8423
Max Act: 4.8076. Min Act: -0.0001
Data Index: 314166 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8423. Min Range: -4.8423
Max Act: 4.6059. Min Act: -0.0001
Data Index: 574511 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8423. Min Range: -4.8423
Max Act: 4.6452. Min Act: -0.0001
Data Index: 720233 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8423. Min Range: -4.8423
Max Act: 4.4259. Min Act: -0.0001
Data Index: 1045566 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8423. Min Range: -4.8423
Max Act: 4.3608. Min Act: -0.0001
Data Index: 1200679 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8423. Min Range: -4.8423
Max Act: 4.5345. Min Act: -0.0002
Data Index: 1003386 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8423. Min Range: -4.8423
Max Act: 4.5275. Min Act: -0.0001
Data Index: 911264 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8423. Min Range: -4.8423
Max Act: 4.6003. Min Act: -0.0001
Data Index: 989553 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8423. Min Range: -4.8423
Max Act: 4.7069. Min Act: -0.0001
Data Index: 1197078 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8423. Min Range: -4.8423
Max Act: 4.2486. Min Act: -0.0001
Data Index: 917240 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8423. Min Range: -4.8423
Max Act: 4.4132. Min Act: -0.0001
Data Index: 558692 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8423. Min Range: -4.8423
Max Act: 4.5482. Min Act: -0.0001
Data Index: 447501 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8423. Min Range: -4.8423
Max Act: 4.6543. Min Act: -0.0001
Data Index: 516542 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8423. Min Range: -4.8423
Max Act: 4.2111. Min Act: -0.0001
Data Index: 953585 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8423. Min Range: -4.8423
Max Act: 4.6200. Min Act: -0.0001
Data Index: 415480 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8423. Min Range: -4.8423
Max Act: 4.5814. Min Act: -0.0001
Data Index: 1349294 (C4 (Web Text))
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8423. Min Range: -4.8423
Max Act: 4.5845. Min Act: -0.0001
Data Index: 944134 (C4 (Web Text))
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8423. Min Range: -4.8423
Max Act: 4.3779. Min Act: -0.0001
Data Index: 43122 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8423. Min Range: -4.8423
Max Act: 4.2284. Min Act: -0.0001
Data Index: 109097 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19