Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3589 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.1176. Min Range: -0.1176
Max Act: 0.1176. Min Act: -0.0001
Data Index: 1578781 (Python Code)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1176. Min Range: -0.1176
Max Act: 0.1045. Min Act: -0.0001
Data Index: 1512113 (Python Code)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1176. Min Range: -0.1176
Max Act: 0.0708. Min Act: -0.0001
Data Index: 1563790 (Python Code)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1176. Min Range: -0.1176
Max Act: 0.0551. Min Act: -0.0001
Data Index: 1199327 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1176. Min Range: -0.1176
Max Act: 0.0746. Min Act: -0.0001
Data Index: 1615414 (Python Code)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1176. Min Range: -0.1176
Max Act: 0.0668. Min Act: -0.0001
Data Index: 1476723 (Python Code)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1176. Min Range: -0.1176
Max Act: 0.0577. Min Act: -0.0001
Data Index: 1620752 (Python Code)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1176. Min Range: -0.1176
Max Act: 0.0560. Min Act: -0.0001
Data Index: 1497825 (Python Code)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1176. Min Range: -0.1176
Max Act: 0.0438. Min Act: -0.0001
Data Index: 1529295 (Python Code)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1176. Min Range: -0.1176
Max Act: 0.0455. Min Act: -0.0001
Data Index: 283935 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1176. Min Range: -0.1176
Max Act: 0.0438. Min Act: -0.0001
Data Index: 1488278 (Python Code)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1176. Min Range: -0.1176
Max Act: 0.0406. Min Act: -0.0001
Data Index: 1589098 (Python Code)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1176. Min Range: -0.1176
Max Act: 0.0412. Min Act: -0.0001
Data Index: 1377253 (Python Code)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1176. Min Range: -0.1176
Max Act: 0.0399. Min Act: -0.0001
Data Index: 1501070 (Python Code)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1176. Min Range: -0.1176
Max Act: 0.0386. Min Act: -0.0001
Data Index: 943093 (C4 (Web Text))
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1176. Min Range: -0.1176
Max Act: 0.0412. Min Act: -0.0001
Data Index: 1370583 (Python Code)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1176. Min Range: -0.1176
Max Act: 0.0393. Min Act: -0.0001
Data Index: 1110973 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1176. Min Range: -0.1176
Max Act: 0.0342. Min Act: -0.0001
Data Index: 1625441 (Python Code)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1176. Min Range: -0.1176
Max Act: 0.0366. Min Act: -0.0001
Data Index: 54852 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1176. Min Range: -0.1176
Max Act: 0.0320. Min Act: -0.0001
Data Index: 1483627 (Python Code)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19