Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1719 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.3019. Min Range: -0.3019
Max Act: 0.3019. Min Act: -0.0001
Data Index: 1378261 (Python Code)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.3019. Min Range: -0.3019
Max Act: 0.2687. Min Act: -0.0001
Data Index: 1368786 (Python Code)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.3019. Min Range: -0.3019
Max Act: 0.2635. Min Act: -0.0001
Data Index: 1437147 (Python Code)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.3019. Min Range: -0.3019
Max Act: 0.2547. Min Act: -0.0001
Data Index: 1609394 (Python Code)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.3019. Min Range: -0.3019
Max Act: 0.2465. Min Act: -0.0001
Data Index: 1480025 (Python Code)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.3019. Min Range: -0.3019
Max Act: 0.2481. Min Act: -0.0001
Data Index: 1367666 (Python Code)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.3019. Min Range: -0.3019
Max Act: 0.2374. Min Act: -0.0001
Data Index: 1585585 (Python Code)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.3019. Min Range: -0.3019
Max Act: 0.2263. Min Act: -0.0001
Data Index: 1421208 (Python Code)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.3019. Min Range: -0.3019
Max Act: 0.2390. Min Act: -0.0001
Data Index: 1394508 (Python Code)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.3019. Min Range: -0.3019
Max Act: 0.2173. Min Act: -0.0001
Data Index: 1378193 (Python Code)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.3019. Min Range: -0.3019
Max Act: 0.2386. Min Act: -0.0001
Data Index: 1341893 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.3019. Min Range: -0.3019
Max Act: 0.2399. Min Act: -0.0001
Data Index: 134679 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.3019. Min Range: -0.3019
Max Act: 0.2314. Min Act: -0.0001
Data Index: 728684 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.3019. Min Range: -0.3019
Max Act: 0.2376. Min Act: -0.0001
Data Index: 904671 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.3019. Min Range: -0.3019
Max Act: 0.2294. Min Act: -0.0001
Data Index: 1595445 (Python Code)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.3019. Min Range: -0.3019
Max Act: 0.2352. Min Act: -0.0001
Data Index: 1171400 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.3019. Min Range: -0.3019
Max Act: 0.2355. Min Act: -0.0001
Data Index: 1453949 (Python Code)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.3019. Min Range: -0.3019
Max Act: 0.2345. Min Act: -0.0001
Data Index: 1238772 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.3019. Min Range: -0.3019
Max Act: 0.2263. Min Act: -0.0001
Data Index: 1443874 (Python Code)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.3019. Min Range: -0.3019
Max Act: 0.2344. Min Act: -0.0001
Data Index: 1575370 (Python Code)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19