Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 413 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.9496. Min Range: -1.9496
Max Act: 1.8030. Min Act: -0.0001
Data Index: 342392 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9496. Min Range: -1.9496
Max Act: 1.9029. Min Act: -0.0001
Data Index: 22238 (C4 (Web Text))
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9496. Min Range: -1.9496
Max Act: 1.9428. Min Act: -0.0001
Data Index: 1137300 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9496. Min Range: -1.9496
Max Act: 1.8739. Min Act: -0.0001
Data Index: 243257 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9496. Min Range: -1.9496
Max Act: 1.8807. Min Act: -0.0001
Data Index: 285028 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9496. Min Range: -1.9496
Max Act: 1.8096. Min Act: -0.0001
Data Index: 430210 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9496. Min Range: -1.9496
Max Act: 1.9496. Min Act: -0.0001
Data Index: 394440 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9496. Min Range: -1.9496
Max Act: 1.8047. Min Act: -0.0001
Data Index: 722852 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9496. Min Range: -1.9496
Max Act: 1.8811. Min Act: -0.0001
Data Index: 807836 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9496. Min Range: -1.9496
Max Act: 1.7562. Min Act: -0.0001
Data Index: 945936 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9496. Min Range: -1.9496
Max Act: 1.8431. Min Act: -0.0001
Data Index: 785419 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9496. Min Range: -1.9496
Max Act: 1.6848. Min Act: -0.0001
Data Index: 888730 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9496. Min Range: -1.9496
Max Act: 1.7656. Min Act: -0.0001
Data Index: 146499 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9496. Min Range: -1.9496
Max Act: 1.7516. Min Act: -0.0001
Data Index: 1235191 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9496. Min Range: -1.9496
Max Act: 1.6998. Min Act: -0.0001
Data Index: 499530 (C4 (Web Text))
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9496. Min Range: -1.9496
Max Act: 1.7391. Min Act: -0.0001
Data Index: 1006294 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9496. Min Range: -1.9496
Max Act: 1.7267. Min Act: -0.0001
Data Index: 707396 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9496. Min Range: -1.9496
Max Act: 1.7828. Min Act: -0.0001
Data Index: 291450 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9496. Min Range: -1.9496
Max Act: 1.7220. Min Act: -0.0001
Data Index: 1008344 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9496. Min Range: -1.9496
Max Act: 1.7572. Min Act: -0.0001
Data Index: 676241 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19