Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 468 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.4067. Min Range: -1.4067
Max Act: 1.4067. Min Act: -0.0001
Data Index: 1419137 (Python Code)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4067. Min Range: -1.4067
Max Act: 1.3354. Min Act: -0.0001
Data Index: 1485591 (Python Code)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4067. Min Range: -1.4067
Max Act: 1.2874. Min Act: -0.0001
Data Index: 1553876 (Python Code)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4067. Min Range: -1.4067
Max Act: 1.2718. Min Act: -0.0001
Data Index: 1542424 (Python Code)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4067. Min Range: -1.4067
Max Act: 1.2336. Min Act: -0.0001
Data Index: 1457784 (Python Code)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4067. Min Range: -1.4067
Max Act: 1.2309. Min Act: -0.0001
Data Index: 1402568 (Python Code)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4067. Min Range: -1.4067
Max Act: 1.0962. Min Act: -0.0001
Data Index: 1636952 (Python Code)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4067. Min Range: -1.4067
Max Act: 1.1722. Min Act: -0.0001
Data Index: 1463286 (Python Code)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4067. Min Range: -1.4067
Max Act: 1.0747. Min Act: -0.0001
Data Index: 1559881 (Python Code)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4067. Min Range: -1.4067
Max Act: 1.1488. Min Act: -0.0001
Data Index: 1578653 (Python Code)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4067. Min Range: -1.4067
Max Act: 1.1029. Min Act: -0.0001
Data Index: 1426817 (Python Code)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4067. Min Range: -1.4067
Max Act: 1.1529. Min Act: -0.0001
Data Index: 1622430 (Python Code)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4067. Min Range: -1.4067
Max Act: 1.0294. Min Act: -0.0001
Data Index: 1448164 (Python Code)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4067. Min Range: -1.4067
Max Act: 1.0764. Min Act: -0.0001
Data Index: 1643958 (Python Code)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4067. Min Range: -1.4067
Max Act: 1.1617. Min Act: -0.0001
Data Index: 1582353 (Python Code)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4067. Min Range: -1.4067
Max Act: 1.1125. Min Act: -0.0001
Data Index: 1561453 (Python Code)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4067. Min Range: -1.4067
Max Act: 1.0844. Min Act: -0.0001
Data Index: 1580250 (Python Code)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4067. Min Range: -1.4067
Max Act: 1.1006. Min Act: -0.0001
Data Index: 1428403 (Python Code)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4067. Min Range: -1.4067
Max Act: 1.1311. Min Act: -0.0001
Data Index: 1546734 (Python Code)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4067. Min Range: -1.4067
Max Act: 1.1201. Min Act: -0.0001
Data Index: 1544306 (Python Code)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #19