Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1756 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.9509. Min Range: -1.9509
Max Act: 1.9509. Min Act: -0.0001
Data Index: 1259552 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9509. Min Range: -1.9509
Max Act: 1.5345. Min Act: -0.0001
Data Index: 83483 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9509. Min Range: -1.9509
Max Act: 1.8225. Min Act: -0.0001
Data Index: 474303 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9509. Min Range: -1.9509
Max Act: 1.6692. Min Act: -0.0001
Data Index: 1039438 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9509. Min Range: -1.9509
Max Act: 1.3325. Min Act: -0.0001
Data Index: 1082542 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9509. Min Range: -1.9509
Max Act: 1.5264. Min Act: -0.0001
Data Index: 1312432 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9509. Min Range: -1.9509
Max Act: 1.6458. Min Act: -0.0001
Data Index: 755557 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9509. Min Range: -1.9509
Max Act: 1.4615. Min Act: -0.0001
Data Index: 674669 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9509. Min Range: -1.9509
Max Act: 1.4384. Min Act: -0.0001
Data Index: 717177 (C4 (Web Text))
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9509. Min Range: -1.9509
Max Act: 1.5657. Min Act: -0.0001
Data Index: 430501 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9509. Min Range: -1.9509
Max Act: 1.4709. Min Act: -0.0001
Data Index: 493205 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9509. Min Range: -1.9509
Max Act: 1.2306. Min Act: -0.0001
Data Index: 995008 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9509. Min Range: -1.9509
Max Act: 1.3739. Min Act: -0.0001
Data Index: 1200655 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9509. Min Range: -1.9509
Max Act: 1.1062. Min Act: -0.0001
Data Index: 1012078 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9509. Min Range: -1.9509
Max Act: 1.3331. Min Act: -0.0001
Data Index: 179092 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9509. Min Range: -1.9509
Max Act: 1.2038. Min Act: -0.0001
Data Index: 344430 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9509. Min Range: -1.9509
Max Act: 1.2038. Min Act: -0.0001
Data Index: 321150 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9509. Min Range: -1.9509
Max Act: 1.1480. Min Act: -0.0001
Data Index: 1086284 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9509. Min Range: -1.9509
Max Act: 1.2067. Min Act: -0.0001
Data Index: 923909 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9509. Min Range: -1.9509
Max Act: 1.1673. Min Act: -0.0001
Data Index: 518573 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19