Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1884 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.2294. Min Range: -1.2294
Max Act: 1.2294. Min Act: -0.0001
Data Index: 1340670 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2294. Min Range: -1.2294
Max Act: 1.1640. Min Act: -0.0001
Data Index: 368295 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2294. Min Range: -1.2294
Max Act: 1.1213. Min Act: -0.0001
Data Index: 89332 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2294. Min Range: -1.2294
Max Act: 1.1782. Min Act: -0.0001
Data Index: 1038540 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2294. Min Range: -1.2294
Max Act: 1.1139. Min Act: -0.0001
Data Index: 1041023 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2294. Min Range: -1.2294
Max Act: 1.0836. Min Act: -0.0001
Data Index: 694106 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2294. Min Range: -1.2294
Max Act: 1.0896. Min Act: -0.0001
Data Index: 783033 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2294. Min Range: -1.2294
Max Act: 1.0801. Min Act: -0.0001
Data Index: 497355 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2294. Min Range: -1.2294
Max Act: 1.1106. Min Act: -0.0001
Data Index: 835179 (C4 (Web Text))
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2294. Min Range: -1.2294
Max Act: 1.0959. Min Act: -0.0001
Data Index: 1523927 (Python Code)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2294. Min Range: -1.2294
Max Act: 1.0259. Min Act: -0.0001
Data Index: 122070 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2294. Min Range: -1.2294
Max Act: 1.0903. Min Act: -0.0001
Data Index: 950950 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2294. Min Range: -1.2294
Max Act: 1.0575. Min Act: -0.0001
Data Index: 1400096 (Python Code)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2294. Min Range: -1.2294
Max Act: 1.1123. Min Act: -0.0001
Data Index: 1201747 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2294. Min Range: -1.2294
Max Act: 1.0398. Min Act: -0.0001
Data Index: 568128 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2294. Min Range: -1.2294
Max Act: 1.0450. Min Act: -0.0001
Data Index: 787418 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2294. Min Range: -1.2294
Max Act: 1.0381. Min Act: -0.0001
Data Index: 831010 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2294. Min Range: -1.2294
Max Act: 1.0350. Min Act: -0.0001
Data Index: 1238389 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2294. Min Range: -1.2294
Max Act: 1.0634. Min Act: -0.0001
Data Index: 1252608 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2294. Min Range: -1.2294
Max Act: 1.0161. Min Act: -0.0001
Data Index: 1131043 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19