Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3087 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.4023. Min Range: -1.4023
Max Act: 1.4023. Min Act: -0.0001
Data Index: 1582210 (Python Code)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4023. Min Range: -1.4023
Max Act: 1.3804. Min Act: -0.0001
Data Index: 1598913 (Python Code)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4023. Min Range: -1.4023
Max Act: 1.3167. Min Act: -0.0001
Data Index: 1377741 (Python Code)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4023. Min Range: -1.4023
Max Act: 1.2738. Min Act: -0.0001
Data Index: 1535128 (Python Code)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4023. Min Range: -1.4023
Max Act: 1.2363. Min Act: -0.0001
Data Index: 1630676 (Python Code)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4023. Min Range: -1.4023
Max Act: 1.2636. Min Act: -0.0001
Data Index: 1507024 (Python Code)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4023. Min Range: -1.4023
Max Act: 1.2839. Min Act: -0.0001
Data Index: 1620813 (Python Code)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4023. Min Range: -1.4023
Max Act: 1.2048. Min Act: -0.0001
Data Index: 1622509 (Python Code)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4023. Min Range: -1.4023
Max Act: 1.2119. Min Act: -0.0001
Data Index: 891392 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4023. Min Range: -1.4023
Max Act: 1.2634. Min Act: -0.0001
Data Index: 1425542 (Python Code)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4023. Min Range: -1.4023
Max Act: 1.2562. Min Act: -0.0001
Data Index: 1605620 (Python Code)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4023. Min Range: -1.4023
Max Act: 1.1724. Min Act: -0.0001
Data Index: 208528 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4023. Min Range: -1.4023
Max Act: 1.3134. Min Act: -0.0001
Data Index: 1623760 (Python Code)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4023. Min Range: -1.4023
Max Act: 1.2779. Min Act: -0.0001
Data Index: 1366026 (Python Code)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4023. Min Range: -1.4023
Max Act: 1.2023. Min Act: -0.0001
Data Index: 1397561 (Python Code)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4023. Min Range: -1.4023
Max Act: 1.1335. Min Act: -0.0001
Data Index: 1622645 (Python Code)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4023. Min Range: -1.4023
Max Act: 1.1626. Min Act: -0.0001
Data Index: 1599768 (Python Code)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4023. Min Range: -1.4023
Max Act: 1.1522. Min Act: -0.0001
Data Index: 1562044 (Python Code)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4023. Min Range: -1.4023
Max Act: 1.1955. Min Act: -0.0001
Data Index: 1555480 (Python Code)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4023. Min Range: -1.4023
Max Act: 1.1501. Min Act: -0.0001
Data Index: 1483030 (Python Code)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19