Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5104 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.6365. Min Range: -1.6365
Max Act: 1.6365. Min Act: -0.0000
Data Index: 1545056 (Python Code)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6365. Min Range: -1.6365
Max Act: 1.3127. Min Act: -0.0000
Data Index: 1472887 (Python Code)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6365. Min Range: -1.6365
Max Act: 1.2697. Min Act: -0.0000
Data Index: 727169 (C4 (Web Text))
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6365. Min Range: -1.6365
Max Act: 1.1448. Min Act: -0.0000
Data Index: 1367180 (Python Code)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6365. Min Range: -1.6365
Max Act: 1.1171. Min Act: -0.0000
Data Index: 1283338 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6365. Min Range: -1.6365
Max Act: 1.1875. Min Act: -0.0000
Data Index: 894954 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6365. Min Range: -1.6365
Max Act: 1.0917. Min Act: -0.0000
Data Index: 1266626 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6365. Min Range: -1.6365
Max Act: 1.0344. Min Act: -0.0000
Data Index: 796274 (C4 (Web Text))
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6365. Min Range: -1.6365
Max Act: 1.0802. Min Act: -0.0000
Data Index: 623509 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6365. Min Range: -1.6365
Max Act: 1.0059. Min Act: -0.0000
Data Index: 1522877 (Python Code)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6365. Min Range: -1.6365
Max Act: 1.0407. Min Act: -0.0000
Data Index: 1550538 (Python Code)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6365. Min Range: -1.6365
Max Act: 1.0531. Min Act: -0.0000
Data Index: 1312125 (C4 (Web Text))
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6365. Min Range: -1.6365
Max Act: 1.0539. Min Act: -0.0000
Data Index: 1426026 (Python Code)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6365. Min Range: -1.6365
Max Act: 1.0488. Min Act: -0.0000
Data Index: 408869 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6365. Min Range: -1.6365
Max Act: 1.0348. Min Act: -0.0000
Data Index: 1525965 (Python Code)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6365. Min Range: -1.6365
Max Act: 1.0989. Min Act: -0.0000
Data Index: 1339086 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6365. Min Range: -1.6365
Max Act: 1.0016. Min Act: -0.0000
Data Index: 1647689 (Python Code)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6365. Min Range: -1.6365
Max Act: 0.9987. Min Act: -0.0000
Data Index: 885520 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6365. Min Range: -1.6365
Max Act: 0.9560. Min Act: -0.0000
Data Index: 159753 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6365. Min Range: -1.6365
Max Act: 1.1038. Min Act: -0.0000
Data Index: 1044723 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19