Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3431 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.7325. Min Range: -0.7325
Max Act: 0.7325. Min Act: -0.0001
Data Index: 88413 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7325. Min Range: -0.7325
Max Act: 0.7012. Min Act: -0.0001
Data Index: 355846 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7325. Min Range: -0.7325
Max Act: 0.6161. Min Act: -0.0001
Data Index: 872211 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7325. Min Range: -0.7325
Max Act: 0.5210. Min Act: -0.0001
Data Index: 77840 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7325. Min Range: -0.7325
Max Act: 0.4978. Min Act: -0.0001
Data Index: 832160 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7325. Min Range: -0.7325
Max Act: 0.4939. Min Act: -0.0001
Data Index: 802151 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7325. Min Range: -0.7325
Max Act: 0.4687. Min Act: -0.0001
Data Index: 245569 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7325. Min Range: -0.7325
Max Act: 0.4266. Min Act: -0.0001
Data Index: 1324983 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7325. Min Range: -0.7325
Max Act: 0.5606. Min Act: -0.0001
Data Index: 860656 (C4 (Web Text))
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7325. Min Range: -0.7325
Max Act: 0.4574. Min Act: -0.0001
Data Index: 698614 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7325. Min Range: -0.7325
Max Act: 0.3789. Min Act: -0.0001
Data Index: 1162616 (C4 (Web Text))
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7325. Min Range: -0.7325
Max Act: 0.3313. Min Act: -0.0001
Data Index: 821787 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7325. Min Range: -0.7325
Max Act: 0.2883. Min Act: -0.0001
Data Index: 50504 (C4 (Web Text))
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7325. Min Range: -0.7325
Max Act: 0.3564. Min Act: -0.0001
Data Index: 267114 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7325. Min Range: -0.7325
Max Act: 0.3406. Min Act: -0.0001
Data Index: 798426 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7325. Min Range: -0.7325
Max Act: 0.3417. Min Act: -0.0001
Data Index: 971189 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7325. Min Range: -0.7325
Max Act: 0.3446. Min Act: -0.0001
Data Index: 1335407 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7325. Min Range: -0.7325
Max Act: 0.3168. Min Act: -0.0001
Data Index: 434945 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7325. Min Range: -0.7325
Max Act: 0.3102. Min Act: -0.0001
Data Index: 214071 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7325. Min Range: -0.7325
Max Act: 0.3079. Min Act: -0.0001
Data Index: 311968 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19