Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1915 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9517. Min Range: -2.9517
Max Act: 2.9201. Min Act: -0.1700
Data Index: 1641035 (Python Code)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9517. Min Range: -2.9517
Max Act: 2.9201. Min Act: -0.1700
Data Index: 1555435 (Python Code)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9517. Min Range: -2.9517
Max Act: 2.9517. Min Act: -0.1700
Data Index: 1585222 (Python Code)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9517. Min Range: -2.9517
Max Act: 2.8566. Min Act: -0.1700
Data Index: 1488822 (Python Code)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9517. Min Range: -2.9517
Max Act: 2.8407. Min Act: -0.1700
Data Index: 1591234 (Python Code)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9517. Min Range: -2.9517
Max Act: 2.8566. Min Act: -0.1700
Data Index: 1407414 (Python Code)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9517. Min Range: -2.9517
Max Act: 2.8248. Min Act: -0.1700
Data Index: 1127810 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9517. Min Range: -2.9517
Max Act: 2.7929. Min Act: -0.1700
Data Index: 1633596 (Python Code)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9517. Min Range: -2.9517
Max Act: 2.7929. Min Act: -0.1700
Data Index: 155744 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9517. Min Range: -2.9517
Max Act: 2.7451. Min Act: -0.1700
Data Index: 1373228 (Python Code)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9517. Min Range: -2.9517
Max Act: 2.7611. Min Act: -0.1700
Data Index: 1533861 (Python Code)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9517. Min Range: -2.9517
Max Act: 2.7291. Min Act: -0.1700
Data Index: 1635641 (Python Code)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9517. Min Range: -2.9517
Max Act: 2.7451. Min Act: -0.1700
Data Index: 1417894 (Python Code)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9517. Min Range: -2.9517
Max Act: 2.7611. Min Act: -0.1700
Data Index: 1573979 (Python Code)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9517. Min Range: -2.9517
Max Act: 2.7611. Min Act: -0.1700
Data Index: 1630618 (Python Code)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9517. Min Range: -2.9517
Max Act: 2.7291. Min Act: -0.1700
Data Index: 1454696 (Python Code)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9517. Min Range: -2.9517
Max Act: 2.6971. Min Act: -0.1700
Data Index: 1557750 (Python Code)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9517. Min Range: -2.9517
Max Act: 2.7451. Min Act: -0.1700
Data Index: 1644238 (Python Code)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9517. Min Range: -2.9517
Max Act: 2.7291. Min Act: -0.1700
Data Index: 1425820 (Python Code)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9517. Min Range: -2.9517
Max Act: 2.7131. Min Act: -0.1700
Data Index: 1570641 (Python Code)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #19