Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3197 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 4.6589. Min Range: -4.6589
Max Act: 4.6589. Min Act: -0.0001
Data Index: 472385 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6589. Min Range: -4.6589
Max Act: 4.2756. Min Act: -0.0001
Data Index: 573556 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6589. Min Range: -4.6589
Max Act: 4.3338. Min Act: -0.0001
Data Index: 1323083 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6589. Min Range: -4.6589
Max Act: 4.0941. Min Act: -0.0001
Data Index: 18810 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6589. Min Range: -4.6589
Max Act: 3.9070. Min Act: -0.0001
Data Index: 860934 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6589. Min Range: -4.6589
Max Act: 3.9725. Min Act: -0.0001
Data Index: 979751 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6589. Min Range: -4.6589
Max Act: 3.8945. Min Act: -0.0001
Data Index: 427675 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6589. Min Range: -4.6589
Max Act: 3.9033. Min Act: -0.0001
Data Index: 1272080 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6589. Min Range: -4.6589
Max Act: 3.8786. Min Act: -0.0001
Data Index: 448340 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6589. Min Range: -4.6589
Max Act: 3.6979. Min Act: -0.0000
Data Index: 296841 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6589. Min Range: -4.6589
Max Act: 3.9424. Min Act: -0.0001
Data Index: 881292 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6589. Min Range: -4.6589
Max Act: 3.7766. Min Act: -0.0001
Data Index: 169811 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6589. Min Range: -4.6589
Max Act: 3.5810. Min Act: -0.0001
Data Index: 126117 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6589. Min Range: -4.6589
Max Act: 3.5298. Min Act: -0.0000
Data Index: 1146781 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6589. Min Range: -4.6589
Max Act: 3.4647. Min Act: -0.0001
Data Index: 767727 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6589. Min Range: -4.6589
Max Act: 3.1322. Min Act: -0.0001
Data Index: 1059108 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6589. Min Range: -4.6589
Max Act: 3.7481. Min Act: -0.0001
Data Index: 1083701 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6589. Min Range: -4.6589
Max Act: 3.4168. Min Act: -0.0001
Data Index: 460665 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6589. Min Range: -4.6589
Max Act: 2.9755. Min Act: -0.0001
Data Index: 524166 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6589. Min Range: -4.6589
Max Act: 3.4004. Min Act: -0.0001
Data Index: 1183124 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19