Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 321 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.4244. Min Range: -0.4244
Max Act: 0.4244. Min Act: -0.0001
Data Index: 312857 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4244. Min Range: -0.4244
Max Act: 0.4004. Min Act: -0.0001
Data Index: 994920 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4244. Min Range: -0.4244
Max Act: 0.4072. Min Act: -0.0001
Data Index: 1231849 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4244. Min Range: -0.4244
Max Act: 0.3656. Min Act: -0.0001
Data Index: 530559 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4244. Min Range: -0.4244
Max Act: 0.3712. Min Act: -0.0001
Data Index: 1017177 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4244. Min Range: -0.4244
Max Act: 0.3642. Min Act: -0.0001
Data Index: 720884 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4244. Min Range: -0.4244
Max Act: 0.3513. Min Act: -0.0001
Data Index: 172977 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4244. Min Range: -0.4244
Max Act: 0.3498. Min Act: -0.0001
Data Index: 1209114 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4244. Min Range: -0.4244
Max Act: 0.3355. Min Act: -0.0001
Data Index: 222854 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4244. Min Range: -0.4244
Max Act: 0.3311. Min Act: -0.0001
Data Index: 1358894 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4244. Min Range: -0.4244
Max Act: 0.3642. Min Act: -0.0001
Data Index: 35016 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4244. Min Range: -0.4244
Max Act: 0.3387. Min Act: -0.0001
Data Index: 903363 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4244. Min Range: -0.4244
Max Act: 0.3369. Min Act: -0.0001
Data Index: 995417 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4244. Min Range: -0.4244
Max Act: 0.3332. Min Act: -0.0001
Data Index: 723673 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4244. Min Range: -0.4244
Max Act: 0.3241. Min Act: -0.0001
Data Index: 1263886 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4244. Min Range: -0.4244
Max Act: 0.3309. Min Act: -0.0001
Data Index: 144592 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4244. Min Range: -0.4244
Max Act: 0.3270. Min Act: -0.0001
Data Index: 112111 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4244. Min Range: -0.4244
Max Act: 0.3128. Min Act: -0.0001
Data Index: 286659 (C4 (Web Text))
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4244. Min Range: -0.4244
Max Act: 0.3235. Min Act: -0.0001
Data Index: 942572 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4244. Min Range: -0.4244
Max Act: 0.3330. Min Act: -0.0001
Data Index: 199304 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19