Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2156 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.8620. Min Range: -2.8620
Max Act: 2.7279. Min Act: -0.0001
Data Index: 1607535 (Python Code)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8620. Min Range: -2.8620
Max Act: 2.8620. Min Act: -0.0001
Data Index: 1603482 (Python Code)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8620. Min Range: -2.8620
Max Act: 2.5632. Min Act: -0.0001
Data Index: 1400142 (Python Code)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8620. Min Range: -2.8620
Max Act: 2.5929. Min Act: -0.0001
Data Index: 1570141 (Python Code)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8620. Min Range: -2.8620
Max Act: 2.5686. Min Act: -0.0001
Data Index: 1464384 (Python Code)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8620. Min Range: -2.8620
Max Act: 2.7102. Min Act: -0.0001
Data Index: 1584024 (Python Code)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8620. Min Range: -2.8620
Max Act: 2.4112. Min Act: -0.0001
Data Index: 1628169 (Python Code)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8620. Min Range: -2.8620
Max Act: 2.4002. Min Act: -0.0001
Data Index: 1471566 (Python Code)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8620. Min Range: -2.8620
Max Act: 2.2777. Min Act: -0.0001
Data Index: 1607626 (Python Code)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8620. Min Range: -2.8620
Max Act: 2.3261. Min Act: -0.0001
Data Index: 1587420 (Python Code)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8620. Min Range: -2.8620
Max Act: 2.1921. Min Act: -0.0001
Data Index: 1578884 (Python Code)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8620. Min Range: -2.8620
Max Act: 2.2471. Min Act: -0.0001
Data Index: 1582157 (Python Code)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8620. Min Range: -2.8620
Max Act: 2.3690. Min Act: -0.0001
Data Index: 1490522 (Python Code)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8620. Min Range: -2.8620
Max Act: 2.1354. Min Act: -0.0001
Data Index: 1468595 (Python Code)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8620. Min Range: -2.8620
Max Act: 2.3548. Min Act: -0.0001
Data Index: 1622525 (Python Code)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8620. Min Range: -2.8620
Max Act: 2.0328. Min Act: -0.0001
Data Index: 1414864 (Python Code)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8620. Min Range: -2.8620
Max Act: 2.2801. Min Act: -0.0001
Data Index: 1376050 (Python Code)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8620. Min Range: -2.8620
Max Act: 2.2696. Min Act: -0.0001
Data Index: 1463705 (Python Code)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8620. Min Range: -2.8620
Max Act: 2.1514. Min Act: -0.0001
Data Index: 1402638 (Python Code)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8620. Min Range: -2.8620
Max Act: 2.2417. Min Act: -0.0001
Data Index: 1608100 (Python Code)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19