Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3759 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.3338. Min Range: -0.3338
Max Act: 0.3163. Min Act: -0.0001
Data Index: 1201088 (C4 (Web Text))
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.3338. Min Range: -0.3338
Max Act: 0.3338. Min Act: -0.0001
Data Index: 1290761 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.3338. Min Range: -0.3338
Max Act: 0.3071. Min Act: -0.0001
Data Index: 440401 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.3338. Min Range: -0.3338
Max Act: 0.3121. Min Act: -0.0001
Data Index: 860698 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.3338. Min Range: -0.3338
Max Act: 0.3055. Min Act: -0.0001
Data Index: 61168 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.3338. Min Range: -0.3338
Max Act: 0.2960. Min Act: -0.0001
Data Index: 421344 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.3338. Min Range: -0.3338
Max Act: 0.2976. Min Act: -0.0001
Data Index: 152133 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.3338. Min Range: -0.3338
Max Act: 0.2882. Min Act: -0.0001
Data Index: 123702 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.3338. Min Range: -0.3338
Max Act: 0.2975. Min Act: -0.0001
Data Index: 681580 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.3338. Min Range: -0.3338
Max Act: 0.3090. Min Act: -0.0001
Data Index: 344470 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.3338. Min Range: -0.3338
Max Act: 0.3044. Min Act: -0.0001
Data Index: 729279 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.3338. Min Range: -0.3338
Max Act: 0.3132. Min Act: -0.0001
Data Index: 1176704 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.3338. Min Range: -0.3338
Max Act: 0.2928. Min Act: -0.0001
Data Index: 1319860 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.3338. Min Range: -0.3338
Max Act: 0.2918. Min Act: -0.0001
Data Index: 433377 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.3338. Min Range: -0.3338
Max Act: 0.3031. Min Act: -0.0001
Data Index: 199540 (C4 (Web Text))
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.3338. Min Range: -0.3338
Max Act: 0.2696. Min Act: -0.0001
Data Index: 1079377 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.3338. Min Range: -0.3338
Max Act: 0.3014. Min Act: -0.0001
Data Index: 420891 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.3338. Min Range: -0.3338
Max Act: 0.2831. Min Act: -0.0001
Data Index: 270765 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.3338. Min Range: -0.3338
Max Act: 0.2942. Min Act: -0.0001
Data Index: 952311 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.3338. Min Range: -0.3338
Max Act: 0.3056. Min Act: -0.0001
Data Index: 827982 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19