Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2917 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.0544. Min Range: -3.0544
Max Act: 3.0544. Min Act: -0.0001
Data Index: 1585498 (Python Code)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0544. Min Range: -3.0544
Max Act: 2.8827. Min Act: -0.0001
Data Index: 1476777 (Python Code)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0544. Min Range: -3.0544
Max Act: 3.0205. Min Act: -0.0001
Data Index: 1576107 (Python Code)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0544. Min Range: -3.0544
Max Act: 2.8373. Min Act: -0.0001
Data Index: 1383289 (Python Code)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0544. Min Range: -3.0544
Max Act: 2.8308. Min Act: -0.0001
Data Index: 1411527 (Python Code)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0544. Min Range: -3.0544
Max Act: 2.7632. Min Act: -0.0001
Data Index: 1641130 (Python Code)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0544. Min Range: -3.0544
Max Act: 2.7613. Min Act: -0.0001
Data Index: 1557445 (Python Code)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0544. Min Range: -3.0544
Max Act: 2.4178. Min Act: -0.0001
Data Index: 1577171 (Python Code)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0544. Min Range: -3.0544
Max Act: 2.6629. Min Act: -0.0001
Data Index: 1577530 (Python Code)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0544. Min Range: -3.0544
Max Act: 2.7897. Min Act: -0.0001
Data Index: 1520968 (Python Code)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0544. Min Range: -3.0544
Max Act: 2.5248. Min Act: -0.0001
Data Index: 1364339 (Python Code)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0544. Min Range: -3.0544
Max Act: 2.5181. Min Act: -0.0001
Data Index: 1423524 (Python Code)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0544. Min Range: -3.0544
Max Act: 2.6220. Min Act: -0.0001
Data Index: 1482962 (Python Code)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0544. Min Range: -3.0544
Max Act: 2.7565. Min Act: -0.0001
Data Index: 1389855 (Python Code)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0544. Min Range: -3.0544
Max Act: 2.5785. Min Act: -0.0001
Data Index: 1577588 (Python Code)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0544. Min Range: -3.0544
Max Act: 2.4423. Min Act: -0.0001
Data Index: 1631412 (Python Code)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0544. Min Range: -3.0544
Max Act: 2.4343. Min Act: -0.0001
Data Index: 1475895 (Python Code)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0544. Min Range: -3.0544
Max Act: 2.6751. Min Act: -0.0001
Data Index: 1629232 (Python Code)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0544. Min Range: -3.0544
Max Act: 2.5317. Min Act: -0.0001
Data Index: 1510084 (Python Code)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0544. Min Range: -3.0544
Max Act: 2.3004. Min Act: -0.0001
Data Index: 1605442 (Python Code)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19