Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3622 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.8978. Min Range: -0.8978
Max Act: 0.8978. Min Act: -0.0001
Data Index: 351120 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8978. Min Range: -0.8978
Max Act: 0.8758. Min Act: -0.0001
Data Index: 1028666 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8978. Min Range: -0.8978
Max Act: 0.8397. Min Act: -0.0001
Data Index: 839072 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8978. Min Range: -0.8978
Max Act: 0.8052. Min Act: -0.0001
Data Index: 173332 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8978. Min Range: -0.8978
Max Act: 0.7925. Min Act: -0.0001
Data Index: 1296457 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8978. Min Range: -0.8978
Max Act: 0.7896. Min Act: -0.0001
Data Index: 143212 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8978. Min Range: -0.8978
Max Act: 0.7080. Min Act: -0.0001
Data Index: 1296045 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8978. Min Range: -0.8978
Max Act: 0.6769. Min Act: -0.0001
Data Index: 302725 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8978. Min Range: -0.8978
Max Act: 0.6879. Min Act: -0.0001
Data Index: 867843 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8978. Min Range: -0.8978
Max Act: 0.6779. Min Act: -0.0001
Data Index: 506982 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8978. Min Range: -0.8978
Max Act: 0.7077. Min Act: -0.0001
Data Index: 312154 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8978. Min Range: -0.8978
Max Act: 0.6896. Min Act: -0.0001
Data Index: 386247 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8978. Min Range: -0.8978
Max Act: 0.6624. Min Act: -0.0001
Data Index: 438875 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8978. Min Range: -0.8978
Max Act: 0.6383. Min Act: -0.0001
Data Index: 1268413 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8978. Min Range: -0.8978
Max Act: 0.6573. Min Act: -0.0001
Data Index: 1346977 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8978. Min Range: -0.8978
Max Act: 0.6527. Min Act: -0.0001
Data Index: 432292 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8978. Min Range: -0.8978
Max Act: 0.6137. Min Act: -0.0001
Data Index: 624808 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8978. Min Range: -0.8978
Max Act: 0.6186. Min Act: -0.0001
Data Index: 707691 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8978. Min Range: -0.8978
Max Act: 0.6126. Min Act: -0.0001
Data Index: 1135240 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8978. Min Range: -0.8978
Max Act: 0.6428. Min Act: -0.0001
Data Index: 528387 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19