Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1580 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 6.0759. Min Range: -6.0759
Max Act: 6.0759. Min Act: -0.0001
Data Index: 1377560 (Python Code)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0759. Min Range: -6.0759
Max Act: 5.9081. Min Act: -0.0001
Data Index: 1540430 (Python Code)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0759. Min Range: -6.0759
Max Act: 5.0177. Min Act: -0.0001
Data Index: 1401324 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0759. Min Range: -6.0759
Max Act: 4.4696. Min Act: -0.0001
Data Index: 1467926 (Python Code)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0759. Min Range: -6.0759
Max Act: 4.8392. Min Act: -0.0001
Data Index: 1585527 (Python Code)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0759. Min Range: -6.0759
Max Act: 4.4038. Min Act: -0.0001
Data Index: 1417817 (Python Code)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0759. Min Range: -6.0759
Max Act: 4.7521. Min Act: -0.0001
Data Index: 1511663 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0759. Min Range: -6.0759
Max Act: 4.5474. Min Act: -0.0001
Data Index: 1586960 (Python Code)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0759. Min Range: -6.0759
Max Act: 4.7021. Min Act: -0.0001
Data Index: 1467561 (Python Code)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0759. Min Range: -6.0759
Max Act: 4.5931. Min Act: -0.0001
Data Index: 1378967 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0759. Min Range: -6.0759
Max Act: 4.5935. Min Act: -0.0001
Data Index: 1384069 (Python Code)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0759. Min Range: -6.0759
Max Act: 4.3203. Min Act: -0.0001
Data Index: 1517316 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0759. Min Range: -6.0759
Max Act: 4.4461. Min Act: -0.0001
Data Index: 1396415 (Python Code)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0759. Min Range: -6.0759
Max Act: 4.1033. Min Act: -0.0001
Data Index: 1652379 (Python Code)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0759. Min Range: -6.0759
Max Act: 4.4250. Min Act: -0.0001
Data Index: 1653122 (Python Code)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0759. Min Range: -6.0759
Max Act: 4.2312. Min Act: -0.0001
Data Index: 1428622 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0759. Min Range: -6.0759
Max Act: 4.3696. Min Act: -0.0001
Data Index: 1550992 (Python Code)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0759. Min Range: -6.0759
Max Act: 4.3768. Min Act: -0.0001
Data Index: 1528271 (Python Code)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0759. Min Range: -6.0759
Max Act: 4.3942. Min Act: -0.0001
Data Index: 1523001 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0759. Min Range: -6.0759
Max Act: 4.2241. Min Act: -0.0001
Data Index: 1406464 (Python Code)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19