Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 13 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.7517. Min Range: -2.7517
Max Act: 2.6252. Min Act: -0.0001
Data Index: 4320 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7517. Min Range: -2.7517
Max Act: 2.7517. Min Act: -0.0001
Data Index: 312759 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7517. Min Range: -2.7517
Max Act: 2.4145. Min Act: -0.0001
Data Index: 961412 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7517. Min Range: -2.7517
Max Act: 2.5692. Min Act: -0.0001
Data Index: 712044 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7517. Min Range: -2.7517
Max Act: 2.4415. Min Act: -0.0001
Data Index: 369329 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7517. Min Range: -2.7517
Max Act: 2.1891. Min Act: -0.0001
Data Index: 958488 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7517. Min Range: -2.7517
Max Act: 2.0353. Min Act: -0.0001
Data Index: 711640 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7517. Min Range: -2.7517
Max Act: 2.1151. Min Act: -0.0001
Data Index: 1030670 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7517. Min Range: -2.7517
Max Act: 1.9657. Min Act: -0.0001
Data Index: 357141 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7517. Min Range: -2.7517
Max Act: 2.1565. Min Act: -0.0001
Data Index: 1044823 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7517. Min Range: -2.7517
Max Act: 1.9259. Min Act: -0.0001
Data Index: 897272 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7517. Min Range: -2.7517
Max Act: 2.1415. Min Act: -0.0001
Data Index: 235675 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7517. Min Range: -2.7517
Max Act: 2.0072. Min Act: -0.0001
Data Index: 156995 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7517. Min Range: -2.7517
Max Act: 2.0061. Min Act: -0.0001
Data Index: 46711 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7517. Min Range: -2.7517
Max Act: 2.1819. Min Act: -0.0001
Data Index: 441965 (C4 (Web Text))
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7517. Min Range: -2.7517
Max Act: 1.9531. Min Act: -0.0001
Data Index: 871897 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7517. Min Range: -2.7517
Max Act: 1.9217. Min Act: -0.0001
Data Index: 587983 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7517. Min Range: -2.7517
Max Act: 1.7346. Min Act: -0.0000
Data Index: 843315 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7517. Min Range: -2.7517
Max Act: 2.1296. Min Act: -0.0001
Data Index: 278966 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7517. Min Range: -2.7517
Max Act: 1.9135. Min Act: -0.0001
Data Index: 82338 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19