Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4466 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.1595. Min Range: -1.1595
Max Act: 1.0895. Min Act: -0.0001
Data Index: 1544740 (Python Code)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1595. Min Range: -1.1595
Max Act: 1.0480. Min Act: -0.0001
Data Index: 372148 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1595. Min Range: -1.1595
Max Act: 1.0248. Min Act: -0.0001
Data Index: 1368549 (Python Code)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1595. Min Range: -1.1595
Max Act: 1.0089. Min Act: -0.0001
Data Index: 754308 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1595. Min Range: -1.1595
Max Act: 1.1595. Min Act: -0.0001
Data Index: 1532305 (Python Code)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1595. Min Range: -1.1595
Max Act: 0.9244. Min Act: -0.0001
Data Index: 1532025 (Python Code)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1595. Min Range: -1.1595
Max Act: 0.9427. Min Act: -0.0001
Data Index: 1632640 (Python Code)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1595. Min Range: -1.1595
Max Act: 0.9097. Min Act: -0.0001
Data Index: 1626604 (Python Code)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1595. Min Range: -1.1595
Max Act: 0.8986. Min Act: -0.0001
Data Index: 1270880 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1595. Min Range: -1.1595
Max Act: 0.8889. Min Act: -0.0001
Data Index: 1574176 (Python Code)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1595. Min Range: -1.1595
Max Act: 0.9161. Min Act: -0.0001
Data Index: 1398974 (Python Code)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1595. Min Range: -1.1595
Max Act: 0.8563. Min Act: -0.0001
Data Index: 950554 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1595. Min Range: -1.1595
Max Act: 0.7765. Min Act: -0.0001
Data Index: 1501399 (Python Code)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1595. Min Range: -1.1595
Max Act: 0.7052. Min Act: -0.0001
Data Index: 1548165 (Python Code)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1595. Min Range: -1.1595
Max Act: 0.9135. Min Act: -0.0001
Data Index: 951823 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1595. Min Range: -1.1595
Max Act: 0.8986. Min Act: -0.0001
Data Index: 738870 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1595. Min Range: -1.1595
Max Act: 0.8667. Min Act: -0.0001
Data Index: 725318 (C4 (Web Text))
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1595. Min Range: -1.1595
Max Act: 0.8913. Min Act: -0.0001
Data Index: 260955 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1595. Min Range: -1.1595
Max Act: 0.8220. Min Act: -0.0001
Data Index: 1080632 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1595. Min Range: -1.1595
Max Act: 0.9342. Min Act: -0.0001
Data Index: 1636773 (Python Code)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19