Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 641 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.1818. Min Range: -0.1818
Max Act: 0.1687. Min Act: -0.0001
Data Index: 801545 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1818. Min Range: -0.1818
Max Act: 0.1779. Min Act: -0.0001
Data Index: 1385092 (Python Code)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1818. Min Range: -0.1818
Max Act: 0.1730. Min Act: -0.0001
Data Index: 371157 (C4 (Web Text))
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1818. Min Range: -0.1818
Max Act: 0.1818. Min Act: -0.0001
Data Index: 1541678 (Python Code)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1818. Min Range: -0.1818
Max Act: 0.1607. Min Act: -0.0001
Data Index: 1497833 (Python Code)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1818. Min Range: -0.1818
Max Act: 0.1696. Min Act: -0.0001
Data Index: 320113 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1818. Min Range: -0.1818
Max Act: 0.1626. Min Act: -0.0001
Data Index: 829338 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1818. Min Range: -0.1818
Max Act: 0.1549. Min Act: -0.0001
Data Index: 883162 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1818. Min Range: -0.1818
Max Act: 0.1657. Min Act: -0.0001
Data Index: 436436 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1818. Min Range: -0.1818
Max Act: 0.1701. Min Act: -0.0001
Data Index: 16129 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1818. Min Range: -0.1818
Max Act: 0.1491. Min Act: -0.0001
Data Index: 833208 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1818. Min Range: -0.1818
Max Act: 0.1578. Min Act: -0.0001
Data Index: 1093111 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1818. Min Range: -0.1818
Max Act: 0.1495. Min Act: -0.0001
Data Index: 1403577 (Python Code)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1818. Min Range: -0.1818
Max Act: 0.1478. Min Act: -0.0001
Data Index: 617694 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1818. Min Range: -0.1818
Max Act: 0.1461. Min Act: -0.0001
Data Index: 1651699 (Python Code)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1818. Min Range: -0.1818
Max Act: 0.1376. Min Act: -0.0001
Data Index: 1219862 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1818. Min Range: -0.1818
Max Act: 0.1540. Min Act: -0.0001
Data Index: 586426 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1818. Min Range: -0.1818
Max Act: 0.1357. Min Act: -0.0001
Data Index: 153284 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1818. Min Range: -0.1818
Max Act: 0.1414. Min Act: -0.0001
Data Index: 1067406 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1818. Min Range: -0.1818
Max Act: 0.1299. Min Act: -0.0001
Data Index: 1369203 (Python Code)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19