Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2010 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.9799. Min Range: -1.9799
Max Act: 1.8768. Min Act: -0.0001
Data Index: 30151 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9799. Min Range: -1.9799
Max Act: 1.9799. Min Act: -0.0001
Data Index: 859525 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9799. Min Range: -1.9799
Max Act: 1.7529. Min Act: -0.0001
Data Index: 285515 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9799. Min Range: -1.9799
Max Act: 1.7690. Min Act: -0.0001
Data Index: 1108841 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9799. Min Range: -1.9799
Max Act: 1.8676. Min Act: -0.0001
Data Index: 395628 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9799. Min Range: -1.9799
Max Act: 1.5460. Min Act: -0.0001
Data Index: 494447 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9799. Min Range: -1.9799
Max Act: 1.8244. Min Act: -0.0000
Data Index: 1240688 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9799. Min Range: -1.9799
Max Act: 1.6168. Min Act: -0.0001
Data Index: 537539 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9799. Min Range: -1.9799
Max Act: 1.7070. Min Act: -0.0001
Data Index: 214418 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9799. Min Range: -1.9799
Max Act: 1.6650. Min Act: -0.0001
Data Index: 930206 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9799. Min Range: -1.9799
Max Act: 1.6509. Min Act: -0.0001
Data Index: 80242 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9799. Min Range: -1.9799
Max Act: 1.7449. Min Act: -0.0001
Data Index: 106292 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9799. Min Range: -1.9799
Max Act: 1.5459. Min Act: -0.0001
Data Index: 1107373 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9799. Min Range: -1.9799
Max Act: 1.6268. Min Act: -0.0001
Data Index: 1056706 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9799. Min Range: -1.9799
Max Act: 1.5988. Min Act: -0.0001
Data Index: 505419 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9799. Min Range: -1.9799
Max Act: 1.6048. Min Act: -0.0001
Data Index: 824824 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9799. Min Range: -1.9799
Max Act: 1.5014. Min Act: -0.0001
Data Index: 1130575 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9799. Min Range: -1.9799
Max Act: 1.5907. Min Act: -0.0001
Data Index: 1123728 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9799. Min Range: -1.9799
Max Act: 1.5917. Min Act: -0.0001
Data Index: 90888 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9799. Min Range: -1.9799
Max Act: 1.5799. Min Act: -0.0001
Data Index: 877594 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19