Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2577 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.1878. Min Range: -2.1878
Max Act: 2.1878. Min Act: -0.0001
Data Index: 1571778 (Python Code)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1878. Min Range: -2.1878
Max Act: 1.6885. Min Act: -0.0001
Data Index: 1557796 (Python Code)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1878. Min Range: -2.1878
Max Act: 1.6747. Min Act: -0.0001
Data Index: 1471093 (Python Code)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1878. Min Range: -2.1878
Max Act: 1.6735. Min Act: -0.0001
Data Index: 1644585 (Python Code)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1878. Min Range: -2.1878
Max Act: 1.7414. Min Act: -0.0001
Data Index: 1591672 (Python Code)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1878. Min Range: -2.1878
Max Act: 1.6334. Min Act: -0.0001
Data Index: 1538246 (Python Code)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1878. Min Range: -2.1878
Max Act: 1.5565. Min Act: -0.0001
Data Index: 1488321 (Python Code)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1878. Min Range: -2.1878
Max Act: 1.5508. Min Act: -0.0001
Data Index: 1654247 (Python Code)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1878. Min Range: -2.1878
Max Act: 1.5444. Min Act: -0.0001
Data Index: 1526986 (Python Code)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1878. Min Range: -2.1878
Max Act: 1.7132. Min Act: -0.0001
Data Index: 1654103 (Python Code)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1878. Min Range: -2.1878
Max Act: 1.5932. Min Act: -0.0001
Data Index: 1625824 (Python Code)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1878. Min Range: -2.1878
Max Act: 1.4903. Min Act: -0.0001
Data Index: 1577840 (Python Code)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1878. Min Range: -2.1878
Max Act: 1.4974. Min Act: -0.0001
Data Index: 1629436 (Python Code)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1878. Min Range: -2.1878
Max Act: 1.5724. Min Act: -0.0001
Data Index: 1624432 (Python Code)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1878. Min Range: -2.1878
Max Act: 1.5630. Min Act: -0.0001
Data Index: 1378428 (Python Code)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1878. Min Range: -2.1878
Max Act: 1.5438. Min Act: -0.0001
Data Index: 1579161 (Python Code)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1878. Min Range: -2.1878
Max Act: 1.5463. Min Act: -0.0001
Data Index: 1595146 (Python Code)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1878. Min Range: -2.1878
Max Act: 1.4623. Min Act: -0.0001
Data Index: 1638715 (Python Code)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1878. Min Range: -2.1878
Max Act: 1.5463. Min Act: -0.0001
Data Index: 1604784 (Python Code)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1878. Min Range: -2.1878
Max Act: 1.5408. Min Act: -0.0001
Data Index: 1405163 (Python Code)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #19