Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4576 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.4961. Min Range: -2.4961
Max Act: 2.4961. Min Act: -0.0001
Data Index: 25673 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4961. Min Range: -2.4961
Max Act: 2.0597. Min Act: -0.0001
Data Index: 35434 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4961. Min Range: -2.4961
Max Act: 1.7777. Min Act: -0.0001
Data Index: 786040 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4961. Min Range: -2.4961
Max Act: 1.9412. Min Act: -0.0001
Data Index: 468267 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4961. Min Range: -2.4961
Max Act: 1.9373. Min Act: -0.0001
Data Index: 467080 (C4 (Web Text))
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4961. Min Range: -2.4961
Max Act: 1.8853. Min Act: -0.0002
Data Index: 239497 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4961. Min Range: -2.4961
Max Act: 1.7787. Min Act: -0.0001
Data Index: 1208939 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4961. Min Range: -2.4961
Max Act: 1.7890. Min Act: -0.0001
Data Index: 1153301 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4961. Min Range: -2.4961
Max Act: 1.6417. Min Act: -0.0001
Data Index: 114786 (C4 (Web Text))
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4961. Min Range: -2.4961
Max Act: 1.6560. Min Act: -0.0001
Data Index: 1282311 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4961. Min Range: -2.4961
Max Act: 1.7809. Min Act: -0.0001
Data Index: 314030 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4961. Min Range: -2.4961
Max Act: 2.0253. Min Act: -0.0001
Data Index: 793429 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4961. Min Range: -2.4961
Max Act: 1.8293. Min Act: -0.0001
Data Index: 945664 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4961. Min Range: -2.4961
Max Act: 1.8666. Min Act: -0.0001
Data Index: 325683 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4961. Min Range: -2.4961
Max Act: 1.9576. Min Act: -0.0001
Data Index: 431518 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4961. Min Range: -2.4961
Max Act: 1.7152. Min Act: -0.0001
Data Index: 498817 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4961. Min Range: -2.4961
Max Act: 1.8130. Min Act: -0.0001
Data Index: 1017584 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4961. Min Range: -2.4961
Max Act: 1.6074. Min Act: -0.0001
Data Index: 880518 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4961. Min Range: -2.4961
Max Act: 1.4524. Min Act: -0.0001
Data Index: 62712 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4961. Min Range: -2.4961
Max Act: 1.6519. Min Act: -0.0001
Data Index: 1133646 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19