Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2871 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.0783. Min Range: -2.0783
Max Act: 2.0783. Min Act: -0.0001
Data Index: 1599834 (Python Code)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0783. Min Range: -2.0783
Max Act: 2.0110. Min Act: -0.0001
Data Index: 1499549 (Python Code)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0783. Min Range: -2.0783
Max Act: 1.6232. Min Act: -0.0001
Data Index: 1641037 (Python Code)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0783. Min Range: -2.0783
Max Act: 1.8908. Min Act: -0.0001
Data Index: 1454800 (Python Code)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0783. Min Range: -2.0783
Max Act: 1.9670. Min Act: -0.0001
Data Index: 1640494 (Python Code)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0783. Min Range: -2.0783
Max Act: 1.9550. Min Act: -0.0001
Data Index: 1566557 (Python Code)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0783. Min Range: -2.0783
Max Act: 1.9028. Min Act: -0.0001
Data Index: 1524278 (Python Code)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0783. Min Range: -2.0783
Max Act: 1.9012. Min Act: -0.0001
Data Index: 1408210 (Python Code)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0783. Min Range: -2.0783
Max Act: 1.8867. Min Act: -0.0001
Data Index: 1548774 (Python Code)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0783. Min Range: -2.0783
Max Act: 1.9256. Min Act: -0.0001
Data Index: 1621689 (Python Code)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0783. Min Range: -2.0783
Max Act: 1.9638. Min Act: -0.0001
Data Index: 1429503 (Python Code)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0783. Min Range: -2.0783
Max Act: 1.8979. Min Act: -0.0001
Data Index: 1576487 (Python Code)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0783. Min Range: -2.0783
Max Act: 1.9732. Min Act: -0.0001
Data Index: 1573599 (Python Code)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0783. Min Range: -2.0783
Max Act: 1.8449. Min Act: -0.0001
Data Index: 1379508 (Python Code)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0783. Min Range: -2.0783
Max Act: 1.8841. Min Act: -0.0001
Data Index: 1411143 (Python Code)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0783. Min Range: -2.0783
Max Act: 1.7224. Min Act: -0.0001
Data Index: 1468199 (Python Code)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0783. Min Range: -2.0783
Max Act: 1.8655. Min Act: -0.0001
Data Index: 1407516 (Python Code)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0783. Min Range: -2.0783
Max Act: 1.6448. Min Act: -0.0001
Data Index: 1626595 (Python Code)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0783. Min Range: -2.0783
Max Act: 1.7920. Min Act: -0.0001
Data Index: 1443964 (Python Code)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0783. Min Range: -2.0783
Max Act: 1.7319. Min Act: -0.0001
Data Index: 1636407 (Python Code)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19