Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2499 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.4241. Min Range: -0.4241
Max Act: 0.4241. Min Act: -0.0001
Data Index: 1298763 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4241. Min Range: -0.4241
Max Act: 0.3963. Min Act: -0.0001
Data Index: 406837 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4241. Min Range: -0.4241
Max Act: 0.3534. Min Act: -0.0001
Data Index: 1087534 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4241. Min Range: -0.4241
Max Act: 0.3468. Min Act: -0.0001
Data Index: 483798 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4241. Min Range: -0.4241
Max Act: 0.3144. Min Act: -0.0001
Data Index: 784693 (C4 (Web Text))
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4241. Min Range: -0.4241
Max Act: 0.2998. Min Act: -0.0001
Data Index: 353195 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4241. Min Range: -0.4241
Max Act: 0.2975. Min Act: -0.0001
Data Index: 1241503 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4241. Min Range: -0.4241
Max Act: 0.3000. Min Act: -0.0001
Data Index: 1047794 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4241. Min Range: -0.4241
Max Act: 0.2766. Min Act: -0.0001
Data Index: 702090 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4241. Min Range: -0.4241
Max Act: 0.2589. Min Act: -0.0001
Data Index: 1288431 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4241. Min Range: -0.4241
Max Act: 0.2695. Min Act: -0.0001
Data Index: 1147717 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4241. Min Range: -0.4241
Max Act: 0.2896. Min Act: -0.0001
Data Index: 425081 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4241. Min Range: -0.4241
Max Act: 0.2648. Min Act: -0.0001
Data Index: 956791 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4241. Min Range: -0.4241
Max Act: 0.2640. Min Act: -0.0001
Data Index: 32435 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4241. Min Range: -0.4241
Max Act: 0.2721. Min Act: -0.0001
Data Index: 33207 (C4 (Web Text))
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4241. Min Range: -0.4241
Max Act: 0.2718. Min Act: -0.0001
Data Index: 366711 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4241. Min Range: -0.4241
Max Act: 0.2515. Min Act: -0.0001
Data Index: 932417 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4241. Min Range: -0.4241
Max Act: 0.2566. Min Act: -0.0001
Data Index: 1195652 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4241. Min Range: -0.4241
Max Act: 0.2631. Min Act: -0.0001
Data Index: 873589 (C4 (Web Text))
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4241. Min Range: -0.4241
Max Act: 0.2749. Min Act: -0.0001
Data Index: 989571 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19