Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4103 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.3058. Min Range: -1.3058
Max Act: 1.1303. Min Act: -0.0001
Data Index: 840126 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3058. Min Range: -1.3058
Max Act: 1.3058. Min Act: -0.0001
Data Index: 981203 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3058. Min Range: -1.3058
Max Act: 1.2431. Min Act: -0.0001
Data Index: 1058672 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3058. Min Range: -1.3058
Max Act: 1.1251. Min Act: -0.0001
Data Index: 46536 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3058. Min Range: -1.3058
Max Act: 0.9833. Min Act: -0.0001
Data Index: 1215795 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3058. Min Range: -1.3058
Max Act: 1.0921. Min Act: -0.0001
Data Index: 1575545 (Python Code)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3058. Min Range: -1.3058
Max Act: 1.1433. Min Act: -0.0001
Data Index: 321950 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3058. Min Range: -1.3058
Max Act: 1.0197. Min Act: -0.0001
Data Index: 1615749 (Python Code)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3058. Min Range: -1.3058
Max Act: 1.0967. Min Act: -0.0001
Data Index: 250781 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3058. Min Range: -1.3058
Max Act: 1.0707. Min Act: -0.0001
Data Index: 1181562 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3058. Min Range: -1.3058
Max Act: 0.9611. Min Act: -0.0001
Data Index: 711721 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3058. Min Range: -1.3058
Max Act: 1.0424. Min Act: -0.0001
Data Index: 764304 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3058. Min Range: -1.3058
Max Act: 1.0704. Min Act: -0.0001
Data Index: 49294 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3058. Min Range: -1.3058
Max Act: 0.9821. Min Act: -0.0001
Data Index: 649430 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3058. Min Range: -1.3058
Max Act: 0.9575. Min Act: -0.0001
Data Index: 415339 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3058. Min Range: -1.3058
Max Act: 0.9665. Min Act: -0.0001
Data Index: 1652151 (Python Code)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3058. Min Range: -1.3058
Max Act: 1.0579. Min Act: -0.0001
Data Index: 762596 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3058. Min Range: -1.3058
Max Act: 0.9570. Min Act: -0.0001
Data Index: 1510163 (Python Code)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3058. Min Range: -1.3058
Max Act: 0.8738. Min Act: -0.0001
Data Index: 1037292 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3058. Min Range: -1.3058
Max Act: 1.0142. Min Act: -0.0001
Data Index: 128315 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19