Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2826 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.5428. Min Range: -0.5428
Max Act: 0.5244. Min Act: -0.0001
Data Index: 182804 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5428. Min Range: -0.5428
Max Act: 0.4881. Min Act: -0.0001
Data Index: 474533 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5428. Min Range: -0.5428
Max Act: 0.5428. Min Act: -0.0001
Data Index: 202182 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5428. Min Range: -0.5428
Max Act: 0.4922. Min Act: -0.0001
Data Index: 813074 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5428. Min Range: -0.5428
Max Act: 0.4727. Min Act: -0.0001
Data Index: 748758 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5428. Min Range: -0.5428
Max Act: 0.5353. Min Act: -0.0001
Data Index: 1097188 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5428. Min Range: -0.5428
Max Act: 0.4756. Min Act: -0.0001
Data Index: 1072238 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5428. Min Range: -0.5428
Max Act: 0.4846. Min Act: -0.0001
Data Index: 298687 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5428. Min Range: -0.5428
Max Act: 0.4259. Min Act: -0.0001
Data Index: 682553 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5428. Min Range: -0.5428
Max Act: 0.4630. Min Act: -0.0001
Data Index: 1229700 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5428. Min Range: -0.5428
Max Act: 0.4177. Min Act: -0.0001
Data Index: 992215 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5428. Min Range: -0.5428
Max Act: 0.4411. Min Act: -0.0001
Data Index: 1186853 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5428. Min Range: -0.5428
Max Act: 0.4538. Min Act: -0.0001
Data Index: 257500 (C4 (Web Text))
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5428. Min Range: -0.5428
Max Act: 0.4359. Min Act: -0.0001
Data Index: 1338336 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5428. Min Range: -0.5428
Max Act: 0.4190. Min Act: -0.0001
Data Index: 647604 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5428. Min Range: -0.5428
Max Act: 0.4428. Min Act: -0.0001
Data Index: 431304 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5428. Min Range: -0.5428
Max Act: 0.4139. Min Act: -0.0001
Data Index: 1025912 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5428. Min Range: -0.5428
Max Act: 0.4746. Min Act: -0.0001
Data Index: 1161152 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5428. Min Range: -0.5428
Max Act: 0.4674. Min Act: -0.0001
Data Index: 1276588 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5428. Min Range: -0.5428
Max Act: 0.4224. Min Act: -0.0001
Data Index: 1137087 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #19