Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 199 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.8897. Min Act: -0.1700
Data Index: 1508592 (Python Code)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.8738. Min Act: -0.1700
Data Index: 1534530 (Python Code)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.8420. Min Act: -0.1700
Data Index: 223060 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.8579. Min Act: -0.1700
Data Index: 1526331 (Python Code)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.8420. Min Act: -0.1700
Data Index: 1525317 (Python Code)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.8579. Min Act: -0.1700
Data Index: 1401390 (Python Code)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.8420. Min Act: -0.1700
Data Index: 1051191 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.8261. Min Act: -0.1700
Data Index: 1392337 (Python Code)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.8420. Min Act: -0.1700
Data Index: 1129231 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.8102. Min Act: -0.1700
Data Index: 1425098 (Python Code)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.8261. Min Act: -0.1700
Data Index: 1564719 (Python Code)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.8420. Min Act: -0.1700
Data Index: 1499063 (Python Code)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.8420. Min Act: -0.1700
Data Index: 1497607 (Python Code)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.8420. Min Act: -0.1700
Data Index: 1369145 (Python Code)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.8261. Min Act: -0.1700
Data Index: 1526766 (Python Code)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.8261. Min Act: -0.1700
Data Index: 1647097 (Python Code)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.8261. Min Act: -0.1700
Data Index: 1462654 (Python Code)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.8420. Min Act: -0.1700
Data Index: 1591437 (Python Code)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.8420. Min Act: -0.1700
Data Index: 1365778 (Python Code)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8897. Min Range: -2.8897
Max Act: 2.8261. Min Act: -0.1700
Data Index: 1506795 (Python Code)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19