Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3588 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.2416. Min Range: -2.2416
Max Act: 2.1903. Min Act: -0.0001
Data Index: 1526416 (Python Code)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2416. Min Range: -2.2416
Max Act: 2.1015. Min Act: -0.0001
Data Index: 1656564 (Python Code)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2416. Min Range: -2.2416
Max Act: 2.1290. Min Act: -0.0001
Data Index: 1538171 (Python Code)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2416. Min Range: -2.2416
Max Act: 2.2416. Min Act: -0.0001
Data Index: 1373868 (Python Code)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2416. Min Range: -2.2416
Max Act: 2.1225. Min Act: -0.0001
Data Index: 1630685 (Python Code)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2416. Min Range: -2.2416
Max Act: 2.1074. Min Act: -0.0001
Data Index: 1478111 (Python Code)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2416. Min Range: -2.2416
Max Act: 2.1695. Min Act: -0.0001
Data Index: 1527126 (Python Code)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2416. Min Range: -2.2416
Max Act: 2.2415. Min Act: -0.0001
Data Index: 1398280 (Python Code)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2416. Min Range: -2.2416
Max Act: 2.0908. Min Act: -0.0001
Data Index: 1577482 (Python Code)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2416. Min Range: -2.2416
Max Act: 2.0773. Min Act: -0.0001
Data Index: 1626127 (Python Code)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2416. Min Range: -2.2416
Max Act: 1.8479. Min Act: -0.0001
Data Index: 1561350 (Python Code)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2416. Min Range: -2.2416
Max Act: 1.9354. Min Act: -0.0001
Data Index: 1537349 (Python Code)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2416. Min Range: -2.2416
Max Act: 2.1900. Min Act: -0.0001
Data Index: 1553887 (Python Code)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2416. Min Range: -2.2416
Max Act: 2.1238. Min Act: -0.0001
Data Index: 1422872 (Python Code)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2416. Min Range: -2.2416
Max Act: 2.1793. Min Act: -0.0001
Data Index: 1611542 (Python Code)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2416. Min Range: -2.2416
Max Act: 1.9696. Min Act: -0.0001
Data Index: 1405127 (Python Code)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2416. Min Range: -2.2416
Max Act: 1.8516. Min Act: -0.0001
Data Index: 1627781 (Python Code)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2416. Min Range: -2.2416
Max Act: 2.0092. Min Act: -0.0001
Data Index: 1530479 (Python Code)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2416. Min Range: -2.2416
Max Act: 1.9370. Min Act: -0.0001
Data Index: 1587553 (Python Code)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2416. Min Range: -2.2416
Max Act: 1.9723. Min Act: -0.0001
Data Index: 1509232 (Python Code)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19