Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3878 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.8104. Min Range: -2.8104
Max Act: 2.8104. Min Act: -0.0001
Data Index: 462113 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8104. Min Range: -2.8104
Max Act: 2.3440. Min Act: -0.0001
Data Index: 1248740 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8104. Min Range: -2.8104
Max Act: 2.1829. Min Act: -0.0001
Data Index: 255738 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8104. Min Range: -2.8104
Max Act: 2.0909. Min Act: -0.0001
Data Index: 1073959 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8104. Min Range: -2.8104
Max Act: 1.9784. Min Act: -0.0001
Data Index: 472880 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8104. Min Range: -2.8104
Max Act: 1.8954. Min Act: -0.0001
Data Index: 1404867 (Python Code)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8104. Min Range: -2.8104
Max Act: 1.9693. Min Act: -0.0001
Data Index: 1522008 (Python Code)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8104. Min Range: -2.8104
Max Act: 1.9211. Min Act: -0.0001
Data Index: 1545893 (Python Code)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8104. Min Range: -2.8104
Max Act: 1.7797. Min Act: -0.0001
Data Index: 1555149 (Python Code)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8104. Min Range: -2.8104
Max Act: 1.9096. Min Act: -0.0001
Data Index: 1578727 (Python Code)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8104. Min Range: -2.8104
Max Act: 1.7546. Min Act: -0.0001
Data Index: 1416543 (Python Code)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8104. Min Range: -2.8104
Max Act: 1.6283. Min Act: -0.0001
Data Index: 1558913 (Python Code)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8104. Min Range: -2.8104
Max Act: 1.7466. Min Act: -0.0001
Data Index: 1605986 (Python Code)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8104. Min Range: -2.8104
Max Act: 1.8222. Min Act: -0.0001
Data Index: 1502552 (Python Code)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8104. Min Range: -2.8104
Max Act: 1.7653. Min Act: -0.0001
Data Index: 1573726 (Python Code)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8104. Min Range: -2.8104
Max Act: 1.7587. Min Act: -0.0001
Data Index: 1557577 (Python Code)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8104. Min Range: -2.8104
Max Act: 1.7465. Min Act: -0.0001
Data Index: 1386894 (Python Code)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8104. Min Range: -2.8104
Max Act: 1.7267. Min Act: -0.0001
Data Index: 1546097 (Python Code)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8104. Min Range: -2.8104
Max Act: 1.7643. Min Act: -0.0001
Data Index: 1409420 (Python Code)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8104. Min Range: -2.8104
Max Act: 1.7179. Min Act: -0.0001
Data Index: 1571644 (Python Code)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19