Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5101 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.5229. Min Range: -2.5229
Max Act: 2.5229. Min Act: -0.0001
Data Index: 1180205 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5229. Min Range: -2.5229
Max Act: 1.8742. Min Act: -0.0001
Data Index: 1271074 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5229. Min Range: -2.5229
Max Act: 2.1440. Min Act: -0.0001
Data Index: 623328 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5229. Min Range: -2.5229
Max Act: 2.0944. Min Act: -0.0001
Data Index: 1239464 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5229. Min Range: -2.5229
Max Act: 2.0812. Min Act: -0.0001
Data Index: 1166081 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5229. Min Range: -2.5229
Max Act: 1.8614. Min Act: -0.0001
Data Index: 670785 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5229. Min Range: -2.5229
Max Act: 2.1780. Min Act: -0.0001
Data Index: 84373 (C4 (Web Text))
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5229. Min Range: -2.5229
Max Act: 1.8270. Min Act: -0.0001
Data Index: 476811 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5229. Min Range: -2.5229
Max Act: 2.0300. Min Act: -0.0001
Data Index: 114242 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5229. Min Range: -2.5229
Max Act: 1.9622. Min Act: -0.0001
Data Index: 1364857 (Python Code)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5229. Min Range: -2.5229
Max Act: 1.8806. Min Act: -0.0001
Data Index: 306421 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5229. Min Range: -2.5229
Max Act: 1.8278. Min Act: -0.0001
Data Index: 218544 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5229. Min Range: -2.5229
Max Act: 1.9608. Min Act: -0.0001
Data Index: 306336 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5229. Min Range: -2.5229
Max Act: 2.0125. Min Act: -0.0001
Data Index: 1318349 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5229. Min Range: -2.5229
Max Act: 1.8483. Min Act: -0.0001
Data Index: 630394 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5229. Min Range: -2.5229
Max Act: 2.1142. Min Act: -0.0001
Data Index: 1611828 (Python Code)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5229. Min Range: -2.5229
Max Act: 2.0429. Min Act: -0.0001
Data Index: 488666 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5229. Min Range: -2.5229
Max Act: 1.9151. Min Act: -0.0001
Data Index: 211667 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5229. Min Range: -2.5229
Max Act: 1.8335. Min Act: -0.0001
Data Index: 570686 (C4 (Web Text))
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5229. Min Range: -2.5229
Max Act: 1.6974. Min Act: -0.0001
Data Index: 319992 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19