Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2923 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.4826. Min Range: -3.4826
Max Act: 3.4826. Min Act: -0.0001
Data Index: 1446017 (Python Code)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4826. Min Range: -3.4826
Max Act: 3.2156. Min Act: -0.0001
Data Index: 1471571 (Python Code)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4826. Min Range: -3.4826
Max Act: 3.0573. Min Act: -0.0001
Data Index: 1420591 (Python Code)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4826. Min Range: -3.4826
Max Act: 2.9747. Min Act: -0.0001
Data Index: 1460810 (Python Code)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4826. Min Range: -3.4826
Max Act: 2.8167. Min Act: -0.0001
Data Index: 1489507 (Python Code)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4826. Min Range: -3.4826
Max Act: 2.8539. Min Act: -0.0001
Data Index: 1646186 (Python Code)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4826. Min Range: -3.4826
Max Act: 2.5730. Min Act: -0.0001
Data Index: 1384487 (Python Code)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4826. Min Range: -3.4826
Max Act: 2.8231. Min Act: -0.0001
Data Index: 1360102 (Python Code)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4826. Min Range: -3.4826
Max Act: 2.8141. Min Act: -0.0001
Data Index: 1491072 (Python Code)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4826. Min Range: -3.4826
Max Act: 2.5286. Min Act: -0.0001
Data Index: 1477471 (Python Code)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4826. Min Range: -3.4826
Max Act: 2.9025. Min Act: -0.0001
Data Index: 1518169 (Python Code)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4826. Min Range: -3.4826
Max Act: 2.3772. Min Act: -0.0001
Data Index: 1370795 (Python Code)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4826. Min Range: -3.4826
Max Act: 2.7396. Min Act: -0.0001
Data Index: 1578150 (Python Code)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4826. Min Range: -3.4826
Max Act: 2.7377. Min Act: -0.0001
Data Index: 1648670 (Python Code)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4826. Min Range: -3.4826
Max Act: 2.7288. Min Act: -0.0001
Data Index: 1577630 (Python Code)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4826. Min Range: -3.4826
Max Act: 2.5921. Min Act: -0.0001
Data Index: 1628362 (Python Code)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4826. Min Range: -3.4826
Max Act: 2.5558. Min Act: -0.0001
Data Index: 1505879 (Python Code)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4826. Min Range: -3.4826
Max Act: 2.6444. Min Act: -0.0001
Data Index: 1576611 (Python Code)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4826. Min Range: -3.4826
Max Act: 2.6282. Min Act: -0.0001
Data Index: 1474234 (Python Code)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4826. Min Range: -3.4826
Max Act: 2.6227. Min Act: -0.0001
Data Index: 1625842 (Python Code)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19