Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4189 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.4454. Min Range: -1.4454
Max Act: 1.4454. Min Act: -0.0001
Data Index: 1454503 (Python Code)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4454. Min Range: -1.4454
Max Act: 1.0631. Min Act: -0.0001
Data Index: 12611 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4454. Min Range: -1.4454
Max Act: 1.0858. Min Act: -0.0001
Data Index: 1640508 (Python Code)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4454. Min Range: -1.4454
Max Act: 1.1803. Min Act: -0.0001
Data Index: 743246 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4454. Min Range: -1.4454
Max Act: 1.0463. Min Act: -0.0001
Data Index: 1439394 (Python Code)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4454. Min Range: -1.4454
Max Act: 1.0434. Min Act: -0.0001
Data Index: 374616 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4454. Min Range: -1.4454
Max Act: 0.9370. Min Act: -0.0001
Data Index: 1637247 (Python Code)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4454. Min Range: -1.4454
Max Act: 1.0100. Min Act: -0.0001
Data Index: 1568941 (Python Code)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4454. Min Range: -1.4454
Max Act: 0.9295. Min Act: -0.0001
Data Index: 225045 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4454. Min Range: -1.4454
Max Act: 0.8811. Min Act: -0.0001
Data Index: 31559 (C4 (Web Text))
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4454. Min Range: -1.4454
Max Act: 0.8748. Min Act: -0.0001
Data Index: 1600243 (Python Code)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4454. Min Range: -1.4454
Max Act: 0.9325. Min Act: -0.0001
Data Index: 1516126 (Python Code)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4454. Min Range: -1.4454
Max Act: 0.9340. Min Act: -0.0001
Data Index: 791313 (C4 (Web Text))
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4454. Min Range: -1.4454
Max Act: 0.9816. Min Act: -0.0001
Data Index: 1512094 (Python Code)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4454. Min Range: -1.4454
Max Act: 0.9149. Min Act: -0.0001
Data Index: 1101633 (C4 (Web Text))
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4454. Min Range: -1.4454
Max Act: 0.9966. Min Act: -0.0001
Data Index: 672048 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4454. Min Range: -1.4454
Max Act: 0.9304. Min Act: -0.0001
Data Index: 1480149 (Python Code)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4454. Min Range: -1.4454
Max Act: 0.9275. Min Act: -0.0001
Data Index: 883304 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4454. Min Range: -1.4454
Max Act: 0.9472. Min Act: -0.0001
Data Index: 1466636 (Python Code)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4454. Min Range: -1.4454
Max Act: 0.8996. Min Act: -0.0001
Data Index: 1386524 (Python Code)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19