Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 83 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.1788. Min Range: -6.1788
Max Act: 6.1788. Min Act: -0.1700
Data Index: 1411709 (Python Code)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1788. Min Range: -6.1788
Max Act: 6.1788. Min Act: -0.1700
Data Index: 1373773 (Python Code)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1788. Min Range: -6.1788
Max Act: 6.1163. Min Act: -0.1700
Data Index: 1632472 (Python Code)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1788. Min Range: -6.1788
Max Act: 6.0538. Min Act: -0.1700
Data Index: 1620626 (Python Code)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1788. Min Range: -6.1788
Max Act: 6.0850. Min Act: -0.1700
Data Index: 1521647 (Python Code)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1788. Min Range: -6.1788
Max Act: 6.0538. Min Act: -0.1700
Data Index: 1577388 (Python Code)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1788. Min Range: -6.1788
Max Act: 6.0225. Min Act: -0.1700
Data Index: 1624923 (Python Code)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1788. Min Range: -6.1788
Max Act: 5.9600. Min Act: -0.1700
Data Index: 1360446 (Python Code)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1788. Min Range: -6.1788
Max Act: 5.9913. Min Act: -0.1700
Data Index: 1542816 (Python Code)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1788. Min Range: -6.1788
Max Act: 5.9913. Min Act: -0.1700
Data Index: 1507675 (Python Code)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1788. Min Range: -6.1788
Max Act: 5.9913. Min Act: -0.1700
Data Index: 1608672 (Python Code)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1788. Min Range: -6.1788
Max Act: 5.9288. Min Act: -0.1700
Data Index: 1552493 (Python Code)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1788. Min Range: -6.1788
Max Act: 5.9600. Min Act: -0.1700
Data Index: 1628968 (Python Code)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1788. Min Range: -6.1788
Max Act: 5.9288. Min Act: -0.1700
Data Index: 1632265 (Python Code)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1788. Min Range: -6.1788
Max Act: 5.9288. Min Act: -0.1700
Data Index: 1588165 (Python Code)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1788. Min Range: -6.1788
Max Act: 5.9913. Min Act: -0.1700
Data Index: 1438130 (Python Code)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1788. Min Range: -6.1788
Max Act: 5.8975. Min Act: -0.1700
Data Index: 1612644 (Python Code)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1788. Min Range: -6.1788
Max Act: 5.9288. Min Act: -0.1700
Data Index: 1397947 (Python Code)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1788. Min Range: -6.1788
Max Act: 5.9288. Min Act: -0.1700
Data Index: 1603997 (Python Code)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1788. Min Range: -6.1788
Max Act: 5.9288. Min Act: -0.1700
Data Index: 1372354 (Python Code)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19