Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4508 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.9081. Min Range: -0.9081
Max Act: 0.9081. Min Act: -0.0001
Data Index: 189665 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9081. Min Range: -0.9081
Max Act: 0.7018. Min Act: -0.0001
Data Index: 1135566 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9081. Min Range: -0.9081
Max Act: 0.7180. Min Act: -0.0001
Data Index: 830702 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9081. Min Range: -0.9081
Max Act: 0.7013. Min Act: -0.0001
Data Index: 496474 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9081. Min Range: -0.9081
Max Act: 0.6656. Min Act: -0.0001
Data Index: 577687 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9081. Min Range: -0.9081
Max Act: 0.6758. Min Act: -0.0001
Data Index: 1095164 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9081. Min Range: -0.9081
Max Act: 0.6580. Min Act: -0.0001
Data Index: 159803 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9081. Min Range: -0.9081
Max Act: 0.6497. Min Act: -0.0001
Data Index: 1124819 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9081. Min Range: -0.9081
Max Act: 0.6773. Min Act: -0.0001
Data Index: 661789 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9081. Min Range: -0.9081
Max Act: 0.6800. Min Act: -0.0001
Data Index: 510736 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9081. Min Range: -0.9081
Max Act: 0.6747. Min Act: -0.0001
Data Index: 68503 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9081. Min Range: -0.9081
Max Act: 0.6335. Min Act: -0.0001
Data Index: 508346 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9081. Min Range: -0.9081
Max Act: 0.6545. Min Act: -0.0001
Data Index: 244917 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9081. Min Range: -0.9081
Max Act: 0.6347. Min Act: -0.0001
Data Index: 305983 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9081. Min Range: -0.9081
Max Act: 0.6583. Min Act: -0.0001
Data Index: 1081720 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9081. Min Range: -0.9081
Max Act: 0.6642. Min Act: -0.0001
Data Index: 924887 (C4 (Web Text))
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9081. Min Range: -0.9081
Max Act: 0.6651. Min Act: -0.0001
Data Index: 984677 (C4 (Web Text))
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9081. Min Range: -0.9081
Max Act: 0.7008. Min Act: -0.0001
Data Index: 1348519 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9081. Min Range: -0.9081
Max Act: 0.6518. Min Act: -0.0001
Data Index: 1082387 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9081. Min Range: -0.9081
Max Act: 0.6405. Min Act: -0.0001
Data Index: 1287542 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19