Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2822 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.0993. Min Range: -0.0993
Max Act: 0.0988. Min Act: -0.0001
Data Index: 1009732 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0993. Min Range: -0.0993
Max Act: 0.0993. Min Act: -0.0001
Data Index: 1149101 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0993. Min Range: -0.0993
Max Act: 0.0935. Min Act: -0.0001
Data Index: 959350 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0993. Min Range: -0.0993
Max Act: 0.0861. Min Act: -0.0001
Data Index: 560618 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0993. Min Range: -0.0993
Max Act: 0.0850. Min Act: -0.0001
Data Index: 948569 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0993. Min Range: -0.0993
Max Act: 0.0860. Min Act: -0.0001
Data Index: 17777 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0993. Min Range: -0.0993
Max Act: 0.0914. Min Act: -0.0001
Data Index: 331453 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0993. Min Range: -0.0993
Max Act: 0.0793. Min Act: -0.0001
Data Index: 931603 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0993. Min Range: -0.0993
Max Act: 0.0845. Min Act: -0.0001
Data Index: 816411 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0993. Min Range: -0.0993
Max Act: 0.0758. Min Act: -0.0001
Data Index: 1317324 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0993. Min Range: -0.0993
Max Act: 0.0780. Min Act: -0.0001
Data Index: 500261 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0993. Min Range: -0.0993
Max Act: 0.0771. Min Act: -0.0001
Data Index: 611836 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0993. Min Range: -0.0993
Max Act: 0.0735. Min Act: -0.0001
Data Index: 688379 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0993. Min Range: -0.0993
Max Act: 0.0761. Min Act: -0.0001
Data Index: 1252849 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0993. Min Range: -0.0993
Max Act: 0.0776. Min Act: -0.0001
Data Index: 1187405 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0993. Min Range: -0.0993
Max Act: 0.0725. Min Act: -0.0001
Data Index: 883776 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0993. Min Range: -0.0993
Max Act: 0.0819. Min Act: -0.0001
Data Index: 205680 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0993. Min Range: -0.0993
Max Act: 0.0796. Min Act: -0.0001
Data Index: 1031985 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0993. Min Range: -0.0993
Max Act: 0.0751. Min Act: -0.0001
Data Index: 143147 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0993. Min Range: -0.0993
Max Act: 0.0752. Min Act: -0.0001
Data Index: 830463 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19