Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2282 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.6849. Min Range: -1.6849
Max Act: 1.6849. Min Act: -0.0001
Data Index: 926300 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6849. Min Range: -1.6849
Max Act: 1.1700. Min Act: -0.0001
Data Index: 46995 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6849. Min Range: -1.6849
Max Act: 1.0372. Min Act: -0.0001
Data Index: 1178094 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6849. Min Range: -1.6849
Max Act: 0.9095. Min Act: -0.0001
Data Index: 1551656 (Python Code)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6849. Min Range: -1.6849
Max Act: 0.9393. Min Act: -0.0001
Data Index: 654271 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6849. Min Range: -1.6849
Max Act: 0.9333. Min Act: -0.0001
Data Index: 265637 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6849. Min Range: -1.6849
Max Act: 0.8671. Min Act: -0.0001
Data Index: 188660 (C4 (Web Text))
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6849. Min Range: -1.6849
Max Act: 0.8577. Min Act: -0.0001
Data Index: 82518 (C4 (Web Text))
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6849. Min Range: -1.6849
Max Act: 0.9350. Min Act: -0.0001
Data Index: 1412697 (Python Code)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6849. Min Range: -1.6849
Max Act: 0.8405. Min Act: -0.0001
Data Index: 1182448 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6849. Min Range: -1.6849
Max Act: 0.8535. Min Act: -0.0001
Data Index: 1465380 (Python Code)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6849. Min Range: -1.6849
Max Act: 0.8087. Min Act: -0.0001
Data Index: 578279 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6849. Min Range: -1.6849
Max Act: 0.8350. Min Act: -0.0001
Data Index: 387732 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6849. Min Range: -1.6849
Max Act: 0.8262. Min Act: -0.0001
Data Index: 1593030 (Python Code)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6849. Min Range: -1.6849
Max Act: 0.8207. Min Act: -0.0001
Data Index: 1493870 (Python Code)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6849. Min Range: -1.6849
Max Act: 0.8321. Min Act: -0.0001
Data Index: 1380055 (Python Code)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6849. Min Range: -1.6849
Max Act: 0.8573. Min Act: -0.0001
Data Index: 1516178 (Python Code)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6849. Min Range: -1.6849
Max Act: 0.7650. Min Act: -0.0001
Data Index: 1511043 (Python Code)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6849. Min Range: -1.6849
Max Act: 0.8224. Min Act: -0.0001
Data Index: 1387448 (Python Code)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6849. Min Range: -1.6849
Max Act: 0.7585. Min Act: -0.0001
Data Index: 1515939 (Python Code)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19