Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3484 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.9814. Min Range: -2.9814
Max Act: 2.9814. Min Act: -0.0001
Data Index: 994269 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9814. Min Range: -2.9814
Max Act: 2.5708. Min Act: -0.0001
Data Index: 1053730 (C4 (Web Text))
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9814. Min Range: -2.9814
Max Act: 2.8674. Min Act: -0.0001
Data Index: 1243751 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9814. Min Range: -2.9814
Max Act: 2.4175. Min Act: -0.0001
Data Index: 569246 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9814. Min Range: -2.9814
Max Act: 2.7112. Min Act: -0.0001
Data Index: 1139343 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9814. Min Range: -2.9814
Max Act: 2.5660. Min Act: -0.0001
Data Index: 260041 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9814. Min Range: -2.9814
Max Act: 2.6458. Min Act: -0.0001
Data Index: 1341557 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9814. Min Range: -2.9814
Max Act: 2.6060. Min Act: -0.0001
Data Index: 758453 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9814. Min Range: -2.9814
Max Act: 2.0643. Min Act: -0.0001
Data Index: 870744 (C4 (Web Text))
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9814. Min Range: -2.9814
Max Act: 2.2737. Min Act: -0.0001
Data Index: 1291013 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9814. Min Range: -2.9814
Max Act: 2.3281. Min Act: -0.0001
Data Index: 776491 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9814. Min Range: -2.9814
Max Act: 2.3420. Min Act: -0.0001
Data Index: 408585 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9814. Min Range: -2.9814
Max Act: 2.2267. Min Act: -0.0001
Data Index: 1039018 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9814. Min Range: -2.9814
Max Act: 2.2144. Min Act: -0.0001
Data Index: 553458 (C4 (Web Text))
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9814. Min Range: -2.9814
Max Act: 2.4295. Min Act: -0.0001
Data Index: 873389 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9814. Min Range: -2.9814
Max Act: 2.2550. Min Act: -0.0001
Data Index: 663519 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9814. Min Range: -2.9814
Max Act: 2.1426. Min Act: -0.0001
Data Index: 49718 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9814. Min Range: -2.9814
Max Act: 2.0371. Min Act: -0.0001
Data Index: 1158087 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9814. Min Range: -2.9814
Max Act: 2.3471. Min Act: -0.0001
Data Index: 1290815 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9814. Min Range: -2.9814
Max Act: 1.9952. Min Act: -0.0001
Data Index: 1173009 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19