Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3997 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.0868. Min Range: -2.0868
Max Act: 2.0868. Min Act: -0.0001
Data Index: 171894 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0868. Min Range: -2.0868
Max Act: 1.9665. Min Act: -0.0001
Data Index: 831269 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0868. Min Range: -2.0868
Max Act: 1.7473. Min Act: -0.0001
Data Index: 440541 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0868. Min Range: -2.0868
Max Act: 1.7089. Min Act: -0.0001
Data Index: 1282307 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0868. Min Range: -2.0868
Max Act: 1.7477. Min Act: -0.0001
Data Index: 799018 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0868. Min Range: -2.0868
Max Act: 1.6098. Min Act: -0.0001
Data Index: 1278172 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0868. Min Range: -2.0868
Max Act: 1.5658. Min Act: -0.0001
Data Index: 865877 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0868. Min Range: -2.0868
Max Act: 1.6532. Min Act: -0.0001
Data Index: 766757 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0868. Min Range: -2.0868
Max Act: 1.6505. Min Act: -0.0001
Data Index: 715165 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0868. Min Range: -2.0868
Max Act: 1.5121. Min Act: -0.0001
Data Index: 606418 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0868. Min Range: -2.0868
Max Act: 1.6367. Min Act: -0.0001
Data Index: 1139726 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0868. Min Range: -2.0868
Max Act: 1.5864. Min Act: -0.0001
Data Index: 1058244 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0868. Min Range: -2.0868
Max Act: 1.6191. Min Act: -0.0001
Data Index: 1314124 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0868. Min Range: -2.0868
Max Act: 1.5514. Min Act: -0.0001
Data Index: 260070 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0868. Min Range: -2.0868
Max Act: 1.6357. Min Act: -0.0001
Data Index: 852076 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0868. Min Range: -2.0868
Max Act: 1.5628. Min Act: -0.0001
Data Index: 617949 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0868. Min Range: -2.0868
Max Act: 1.5131. Min Act: -0.0001
Data Index: 1260326 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0868. Min Range: -2.0868
Max Act: 1.5078. Min Act: -0.0001
Data Index: 1193933 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0868. Min Range: -2.0868
Max Act: 1.4903. Min Act: -0.0001
Data Index: 385025 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0868. Min Range: -2.0868
Max Act: 1.5788. Min Act: -0.0001
Data Index: 861460 (C4 (Web Text))
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19