Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 630 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 3.4653. Min Range: -3.4653
Max Act: 3.4653. Min Act: -0.0001
Data Index: 1368689 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4653. Min Range: -3.4653
Max Act: 3.2701. Min Act: -0.0001
Data Index: 1429077 (Python Code)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4653. Min Range: -3.4653
Max Act: 3.0795. Min Act: -0.0001
Data Index: 1417980 (Python Code)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4653. Min Range: -3.4653
Max Act: 2.8169. Min Act: -0.0001
Data Index: 1378288 (Python Code)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4653. Min Range: -3.4653
Max Act: 2.9323. Min Act: -0.0001
Data Index: 1562959 (Python Code)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4653. Min Range: -3.4653
Max Act: 2.6060. Min Act: -0.0001
Data Index: 1560453 (Python Code)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4653. Min Range: -3.4653
Max Act: 2.4538. Min Act: -0.0001
Data Index: 1644053 (Python Code)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4653. Min Range: -3.4653
Max Act: 2.5164. Min Act: -0.0001
Data Index: 1425135 (Python Code)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4653. Min Range: -3.4653
Max Act: 2.3506. Min Act: -0.0001
Data Index: 1575533 (Python Code)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4653. Min Range: -3.4653
Max Act: 2.4489. Min Act: -0.0001
Data Index: 1404892 (Python Code)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4653. Min Range: -3.4653
Max Act: 2.3986. Min Act: -0.0001
Data Index: 1577065 (Python Code)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4653. Min Range: -3.4653
Max Act: 2.3660. Min Act: -0.0001
Data Index: 1497614 (Python Code)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4653. Min Range: -3.4653
Max Act: 2.4469. Min Act: -0.0001
Data Index: 1576393 (Python Code)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4653. Min Range: -3.4653
Max Act: 2.2285. Min Act: -0.0001
Data Index: 1577629 (Python Code)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4653. Min Range: -3.4653
Max Act: 2.2234. Min Act: -0.0001
Data Index: 1456942 (Python Code)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4653. Min Range: -3.4653
Max Act: 2.2203. Min Act: -0.0001
Data Index: 1605855 (Python Code)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4653. Min Range: -3.4653
Max Act: 2.3098. Min Act: -0.0001
Data Index: 1361829 (Python Code)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4653. Min Range: -3.4653
Max Act: 2.1627. Min Act: -0.0001
Data Index: 1415412 (Python Code)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4653. Min Range: -3.4653
Max Act: 2.2979. Min Act: -0.0001
Data Index: 1608367 (Python Code)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4653. Min Range: -3.4653
Max Act: 2.1736. Min Act: -0.0001
Data Index: 1501695 (Python Code)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19