Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 949 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.2731. Min Range: -4.2731
Max Act: 4.2731. Min Act: -0.1700
Data Index: 1591638 (Python Code)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2731. Min Range: -4.2731
Max Act: 4.2106. Min Act: -0.1700
Data Index: 1523889 (Python Code)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2731. Min Range: -4.2731
Max Act: 4.2418. Min Act: -0.1700
Data Index: 1381743 (Python Code)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2731. Min Range: -4.2731
Max Act: 4.2106. Min Act: -0.1700
Data Index: 1502487 (Python Code)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2731. Min Range: -4.2731
Max Act: 4.1793. Min Act: -0.1700
Data Index: 1404420 (Python Code)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2731. Min Range: -4.2731
Max Act: 4.1793. Min Act: -0.1700
Data Index: 1384326 (Python Code)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2731. Min Range: -4.2731
Max Act: 4.1480. Min Act: -0.1700
Data Index: 1454555 (Python Code)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2731. Min Range: -4.2731
Max Act: 4.1480. Min Act: -0.1700
Data Index: 1390760 (Python Code)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2731. Min Range: -4.2731
Max Act: 4.1480. Min Act: -0.1700
Data Index: 1628594 (Python Code)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2731. Min Range: -4.2731
Max Act: 4.1480. Min Act: -0.1700
Data Index: 1427216 (Python Code)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2731. Min Range: -4.2731
Max Act: 4.1168. Min Act: -0.1700
Data Index: 1365069 (Python Code)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2731. Min Range: -4.2731
Max Act: 4.0855. Min Act: -0.1700
Data Index: 1620826 (Python Code)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2731. Min Range: -4.2731
Max Act: 4.0855. Min Act: -0.1700
Data Index: 1606253 (Python Code)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2731. Min Range: -4.2731
Max Act: 4.0855. Min Act: -0.1700
Data Index: 1461032 (Python Code)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2731. Min Range: -4.2731
Max Act: 4.0230. Min Act: -0.1700
Data Index: 1396918 (Python Code)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2731. Min Range: -4.2731
Max Act: 4.0543. Min Act: -0.1700
Data Index: 1388703 (Python Code)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2731. Min Range: -4.2731
Max Act: 4.0230. Min Act: -0.1700
Data Index: 1429344 (Python Code)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2731. Min Range: -4.2731
Max Act: 4.0855. Min Act: -0.1700
Data Index: 1543911 (Python Code)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2731. Min Range: -4.2731
Max Act: 4.0855. Min Act: -0.1700
Data Index: 1490995 (Python Code)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2731. Min Range: -4.2731
Max Act: 4.0543. Min Act: -0.1700
Data Index: 1548523 (Python Code)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19