Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1697 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 4.6228. Min Range: -4.6228
Max Act: 4.6228. Min Act: -0.0001
Data Index: 1627071 (Python Code)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6228. Min Range: -4.6228
Max Act: 4.2269. Min Act: -0.0001
Data Index: 1655517 (Python Code)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6228. Min Range: -4.6228
Max Act: 4.0908. Min Act: -0.0001
Data Index: 1646536 (Python Code)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6228. Min Range: -4.6228
Max Act: 4.0869. Min Act: -0.0001
Data Index: 1514554 (Python Code)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6228. Min Range: -4.6228
Max Act: 4.2321. Min Act: -0.0001
Data Index: 1383891 (Python Code)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6228. Min Range: -4.6228
Max Act: 3.8776. Min Act: -0.0001
Data Index: 1611465 (Python Code)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6228. Min Range: -4.6228
Max Act: 4.0182. Min Act: -0.0001
Data Index: 1397546 (Python Code)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6228. Min Range: -4.6228
Max Act: 4.0071. Min Act: -0.0001
Data Index: 1635494 (Python Code)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6228. Min Range: -4.6228
Max Act: 4.0033. Min Act: -0.0001
Data Index: 1468289 (Python Code)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6228. Min Range: -4.6228
Max Act: 3.6104. Min Act: -0.0001
Data Index: 1366684 (Python Code)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6228. Min Range: -4.6228
Max Act: 3.9599. Min Act: -0.0001
Data Index: 1519892 (Python Code)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6228. Min Range: -4.6228
Max Act: 3.5836. Min Act: -0.0001
Data Index: 1416607 (Python Code)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6228. Min Range: -4.6228
Max Act: 4.0580. Min Act: -0.0001
Data Index: 1368401 (Python Code)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6228. Min Range: -4.6228
Max Act: 4.0043. Min Act: -0.0001
Data Index: 1382206 (Python Code)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6228. Min Range: -4.6228
Max Act: 3.7895. Min Act: -0.0001
Data Index: 1437602 (Python Code)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6228. Min Range: -4.6228
Max Act: 3.7994. Min Act: -0.0001
Data Index: 1528031 (Python Code)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6228. Min Range: -4.6228
Max Act: 3.6004. Min Act: -0.0001
Data Index: 1640164 (Python Code)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6228. Min Range: -4.6228
Max Act: 3.6275. Min Act: -0.0001
Data Index: 1447848 (Python Code)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6228. Min Range: -4.6228
Max Act: 3.7820. Min Act: -0.0001
Data Index: 1575540 (Python Code)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6228. Min Range: -4.6228
Max Act: 3.5981. Min Act: -0.0001
Data Index: 1642946 (Python Code)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19