Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3771 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.9586. Min Range: -0.9586
Max Act: 0.9586. Min Act: -0.0001
Data Index: 1026073 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9586. Min Range: -0.9586
Max Act: 0.8851. Min Act: -0.0001
Data Index: 134146 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9586. Min Range: -0.9586
Max Act: 0.6868. Min Act: -0.0001
Data Index: 1063230 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9586. Min Range: -0.9586
Max Act: 0.6974. Min Act: -0.0001
Data Index: 449995 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9586. Min Range: -0.9586
Max Act: 0.7104. Min Act: -0.0001
Data Index: 1096758 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9586. Min Range: -0.9586
Max Act: 0.6088. Min Act: -0.0001
Data Index: 648355 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9586. Min Range: -0.9586
Max Act: 0.6591. Min Act: -0.0001
Data Index: 145775 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9586. Min Range: -0.9586
Max Act: 0.6074. Min Act: -0.0001
Data Index: 172178 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9586. Min Range: -0.9586
Max Act: 0.6146. Min Act: -0.0001
Data Index: 103696 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9586. Min Range: -0.9586
Max Act: 0.6259. Min Act: -0.0001
Data Index: 517202 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9586. Min Range: -0.9586
Max Act: 0.6107. Min Act: -0.0001
Data Index: 1315452 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9586. Min Range: -0.9586
Max Act: 0.5688. Min Act: -0.0001
Data Index: 809403 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9586. Min Range: -0.9586
Max Act: 0.5628. Min Act: -0.0001
Data Index: 1140206 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9586. Min Range: -0.9586
Max Act: 0.5657. Min Act: -0.0001
Data Index: 1126932 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9586. Min Range: -0.9586
Max Act: 0.5609. Min Act: -0.0001
Data Index: 931957 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9586. Min Range: -0.9586
Max Act: 0.5711. Min Act: -0.0001
Data Index: 307212 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9586. Min Range: -0.9586
Max Act: 0.5473. Min Act: -0.0001
Data Index: 1182769 (C4 (Web Text))
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9586. Min Range: -0.9586
Max Act: 0.6008. Min Act: -0.0001
Data Index: 1316097 (C4 (Web Text))
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9586. Min Range: -0.9586
Max Act: 0.5407. Min Act: -0.0001
Data Index: 1260879 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9586. Min Range: -0.9586
Max Act: 0.5766. Min Act: -0.0001
Data Index: 1152319 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19