Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 115 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.1587. Min Range: -0.1587
Max Act: 0.1549. Min Act: -0.0001
Data Index: 388565 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1587. Min Range: -0.1587
Max Act: 0.1587. Min Act: -0.0001
Data Index: 411639 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1587. Min Range: -0.1587
Max Act: 0.1471. Min Act: -0.0001
Data Index: 475876 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1587. Min Range: -0.1587
Max Act: 0.1513. Min Act: -0.0001
Data Index: 13202 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1587. Min Range: -0.1587
Max Act: 0.1507. Min Act: -0.0001
Data Index: 1175735 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1587. Min Range: -0.1587
Max Act: 0.1417. Min Act: -0.0001
Data Index: 607965 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1587. Min Range: -0.1587
Max Act: 0.1395. Min Act: -0.0001
Data Index: 369174 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1587. Min Range: -0.1587
Max Act: 0.1412. Min Act: -0.0001
Data Index: 1189977 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1587. Min Range: -0.1587
Max Act: 0.1288. Min Act: -0.0001
Data Index: 295893 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1587. Min Range: -0.1587
Max Act: 0.1337. Min Act: -0.0001
Data Index: 1352442 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1587. Min Range: -0.1587
Max Act: 0.1511. Min Act: -0.0001
Data Index: 778743 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1587. Min Range: -0.1587
Max Act: 0.1582. Min Act: -0.0001
Data Index: 1021924 (C4 (Web Text))
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1587. Min Range: -0.1587
Max Act: 0.1334. Min Act: -0.0001
Data Index: 1601053 (Python Code)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1587. Min Range: -0.1587
Max Act: 0.1467. Min Act: -0.0001
Data Index: 25082 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1587. Min Range: -0.1587
Max Act: 0.1421. Min Act: -0.0001
Data Index: 1043122 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1587. Min Range: -0.1587
Max Act: 0.1494. Min Act: -0.0001
Data Index: 755221 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1587. Min Range: -0.1587
Max Act: 0.1342. Min Act: -0.0001
Data Index: 589171 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1587. Min Range: -0.1587
Max Act: 0.1011. Min Act: -0.0001
Data Index: 1115224 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1587. Min Range: -0.1587
Max Act: 0.1274. Min Act: -0.0001
Data Index: 682896 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1587. Min Range: -0.1587
Max Act: 0.1166. Min Act: -0.0001
Data Index: 1544259 (Python Code)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19