Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2771 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.9033. Min Range: -1.9033
Max Act: 1.9033. Min Act: -0.0001
Data Index: 1587724 (Python Code)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9033. Min Range: -1.9033
Max Act: 1.7649. Min Act: -0.0001
Data Index: 1642716 (Python Code)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9033. Min Range: -1.9033
Max Act: 1.7065. Min Act: -0.0001
Data Index: 1419628 (Python Code)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9033. Min Range: -1.9033
Max Act: 1.7495. Min Act: -0.0001
Data Index: 1392387 (Python Code)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9033. Min Range: -1.9033
Max Act: 1.7054. Min Act: -0.0001
Data Index: 1597963 (Python Code)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9033. Min Range: -1.9033
Max Act: 1.5627. Min Act: -0.0001
Data Index: 1653738 (Python Code)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9033. Min Range: -1.9033
Max Act: 1.6605. Min Act: -0.0001
Data Index: 1588403 (Python Code)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9033. Min Range: -1.9033
Max Act: 1.6047. Min Act: -0.0001
Data Index: 1583039 (Python Code)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9033. Min Range: -1.9033
Max Act: 1.6866. Min Act: -0.0001
Data Index: 1468726 (Python Code)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9033. Min Range: -1.9033
Max Act: 1.5998. Min Act: -0.0001
Data Index: 1520997 (Python Code)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9033. Min Range: -1.9033
Max Act: 1.7175. Min Act: -0.0001
Data Index: 1479665 (Python Code)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9033. Min Range: -1.9033
Max Act: 1.5785. Min Act: -0.0001
Data Index: 1552174 (Python Code)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9033. Min Range: -1.9033
Max Act: 1.5969. Min Act: -0.0001
Data Index: 1377326 (Python Code)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9033. Min Range: -1.9033
Max Act: 1.5865. Min Act: -0.0001
Data Index: 1546672 (Python Code)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9033. Min Range: -1.9033
Max Act: 1.4354. Min Act: -0.0001
Data Index: 1544371 (Python Code)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9033. Min Range: -1.9033
Max Act: 1.5553. Min Act: -0.0001
Data Index: 1374604 (Python Code)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9033. Min Range: -1.9033
Max Act: 1.5589. Min Act: -0.0001
Data Index: 1530834 (Python Code)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9033. Min Range: -1.9033
Max Act: 1.5345. Min Act: -0.0001
Data Index: 1589074 (Python Code)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9033. Min Range: -1.9033
Max Act: 1.5374. Min Act: -0.0001
Data Index: 1600829 (Python Code)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9033. Min Range: -1.9033
Max Act: 1.6231. Min Act: -0.0001
Data Index: 1393755 (Python Code)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19