Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3935 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.2028. Min Range: -1.2028
Max Act: 1.2028. Min Act: -0.0001
Data Index: 954952 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2028. Min Range: -1.2028
Max Act: 1.1640. Min Act: -0.0001
Data Index: 1416522 (Python Code)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2028. Min Range: -1.2028
Max Act: 1.1783. Min Act: -0.0001
Data Index: 1649280 (Python Code)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2028. Min Range: -1.2028
Max Act: 1.1506. Min Act: -0.0001
Data Index: 817408 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2028. Min Range: -1.2028
Max Act: 1.1420. Min Act: -0.0001
Data Index: 1447618 (Python Code)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2028. Min Range: -1.2028
Max Act: 1.0019. Min Act: -0.0001
Data Index: 929386 (C4 (Web Text))
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2028. Min Range: -1.2028
Max Act: 1.1332. Min Act: -0.0001
Data Index: 356741 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2028. Min Range: -1.2028
Max Act: 1.0346. Min Act: -0.0001
Data Index: 1355155 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2028. Min Range: -1.2028
Max Act: 1.1316. Min Act: -0.0001
Data Index: 566314 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2028. Min Range: -1.2028
Max Act: 1.1524. Min Act: -0.0001
Data Index: 1328641 (C4 (Web Text))
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2028. Min Range: -1.2028
Max Act: 1.0348. Min Act: -0.0001
Data Index: 1226434 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2028. Min Range: -1.2028
Max Act: 1.0960. Min Act: -0.0001
Data Index: 1602615 (Python Code)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2028. Min Range: -1.2028
Max Act: 1.0853. Min Act: -0.0001
Data Index: 1618502 (Python Code)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2028. Min Range: -1.2028
Max Act: 1.0739. Min Act: -0.0001
Data Index: 1178720 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2028. Min Range: -1.2028
Max Act: 1.0823. Min Act: -0.0001
Data Index: 185442 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2028. Min Range: -1.2028
Max Act: 1.0684. Min Act: -0.0001
Data Index: 805844 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2028. Min Range: -1.2028
Max Act: 1.1368. Min Act: -0.0001
Data Index: 869184 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2028. Min Range: -1.2028
Max Act: 1.0607. Min Act: -0.0001
Data Index: 828689 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2028. Min Range: -1.2028
Max Act: 1.0484. Min Act: -0.0001
Data Index: 875735 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2028. Min Range: -1.2028
Max Act: 1.0575. Min Act: -0.0001
Data Index: 338175 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19