Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2065 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.1655. Min Range: -0.1655
Max Act: 0.1655. Min Act: -0.0001
Data Index: 236878 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1655. Min Range: -0.1655
Max Act: 0.1576. Min Act: -0.0001
Data Index: 1153169 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1655. Min Range: -0.1655
Max Act: 0.1540. Min Act: -0.0001
Data Index: 363832 (C4 (Web Text))
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1655. Min Range: -0.1655
Max Act: 0.1546. Min Act: -0.0001
Data Index: 1565401 (Python Code)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1655. Min Range: -0.1655
Max Act: 0.1481. Min Act: -0.0001
Data Index: 760988 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1655. Min Range: -0.1655
Max Act: 0.1511. Min Act: -0.0001
Data Index: 1123850 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1655. Min Range: -0.1655
Max Act: 0.1455. Min Act: -0.0001
Data Index: 1104447 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1655. Min Range: -0.1655
Max Act: 0.1524. Min Act: -0.0001
Data Index: 561829 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1655. Min Range: -0.1655
Max Act: 0.1460. Min Act: -0.0001
Data Index: 1222969 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1655. Min Range: -0.1655
Max Act: 0.1479. Min Act: -0.0001
Data Index: 1271821 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1655. Min Range: -0.1655
Max Act: 0.1569. Min Act: -0.0001
Data Index: 1597239 (Python Code)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1655. Min Range: -0.1655
Max Act: 0.1358. Min Act: -0.0001
Data Index: 319364 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1655. Min Range: -0.1655
Max Act: 0.1421. Min Act: -0.0001
Data Index: 82425 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1655. Min Range: -0.1655
Max Act: 0.1326. Min Act: -0.0001
Data Index: 30091 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1655. Min Range: -0.1655
Max Act: 0.1386. Min Act: -0.0001
Data Index: 610887 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1655. Min Range: -0.1655
Max Act: 0.1419. Min Act: -0.0001
Data Index: 621828 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1655. Min Range: -0.1655
Max Act: 0.1412. Min Act: -0.0001
Data Index: 206139 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1655. Min Range: -0.1655
Max Act: 0.1421. Min Act: -0.0001
Data Index: 625496 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1655. Min Range: -0.1655
Max Act: 0.1344. Min Act: -0.0001
Data Index: 833244 (C4 (Web Text))
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1655. Min Range: -0.1655
Max Act: 0.1373. Min Act: -0.0001
Data Index: 281533 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19