Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1846 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.0184. Min Range: -6.0184
Max Act: 6.0184. Min Act: -0.1700
Data Index: 1444778 (Python Code)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0184. Min Range: -6.0184
Max Act: 6.0184. Min Act: -0.1700
Data Index: 1430353 (Python Code)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0184. Min Range: -6.0184
Max Act: 5.9559. Min Act: -0.1700
Data Index: 368563 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0184. Min Range: -6.0184
Max Act: 5.9871. Min Act: -0.1700
Data Index: 1608568 (Python Code)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0184. Min Range: -6.0184
Max Act: 5.9559. Min Act: -0.1700
Data Index: 1492183 (Python Code)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0184. Min Range: -6.0184
Max Act: 5.9246. Min Act: -0.1700
Data Index: 1575022 (Python Code)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0184. Min Range: -6.0184
Max Act: 5.8621. Min Act: -0.1700
Data Index: 1178910 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0184. Min Range: -6.0184
Max Act: 5.7684. Min Act: -0.1700
Data Index: 1632954 (Python Code)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0184. Min Range: -6.0184
Max Act: 5.7996. Min Act: -0.1700
Data Index: 877789 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0184. Min Range: -6.0184
Max Act: 5.7371. Min Act: -0.1699
Data Index: 1094009 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0184. Min Range: -6.0184
Max Act: 5.6121. Min Act: -0.1700
Data Index: 1148206 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0184. Min Range: -6.0184
Max Act: 5.6121. Min Act: -0.1700
Data Index: 1647487 (Python Code)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0184. Min Range: -6.0184
Max Act: 5.6121. Min Act: -0.1700
Data Index: 1135660 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0184. Min Range: -6.0184
Max Act: 5.5184. Min Act: -0.1700
Data Index: 885786 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0184. Min Range: -6.0184
Max Act: 5.4871. Min Act: -0.1700
Data Index: 798408 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0184. Min Range: -6.0184
Max Act: 5.5496. Min Act: -0.1700
Data Index: 766875 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0184. Min Range: -6.0184
Max Act: 5.5809. Min Act: -0.1700
Data Index: 95843 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0184. Min Range: -6.0184
Max Act: 5.5184. Min Act: -0.1700
Data Index: 63074 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0184. Min Range: -6.0184
Max Act: 5.4871. Min Act: -0.1699
Data Index: 1348222 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0184. Min Range: -6.0184
Max Act: 5.4871. Min Act: -0.1700
Data Index: 743305 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #19