Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 795 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.3257. Min Range: -2.3257
Max Act: 2.3257. Min Act: -0.1700
Data Index: 1503646 (Python Code)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3257. Min Range: -2.3257
Max Act: 2.2268. Min Act: -0.1697
Data Index: 300431 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3257. Min Range: -2.3257
Max Act: 2.1605. Min Act: -0.1698
Data Index: 866853 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3257. Min Range: -2.3257
Max Act: 2.1438. Min Act: -0.1700
Data Index: 1496791 (Python Code)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3257. Min Range: -2.3257
Max Act: 2.1438. Min Act: -0.1700
Data Index: 1378014 (Python Code)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3257. Min Range: -2.3257
Max Act: 2.0602. Min Act: -0.1700
Data Index: 1459517 (Python Code)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3257. Min Range: -2.3257
Max Act: 2.0769. Min Act: -0.1700
Data Index: 1636393 (Python Code)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3257. Min Range: -2.3257
Max Act: 2.0434. Min Act: -0.1700
Data Index: 1434788 (Python Code)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3257. Min Range: -2.3257
Max Act: 2.0602. Min Act: -0.1700
Data Index: 1542754 (Python Code)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3257. Min Range: -2.3257
Max Act: 2.0265. Min Act: -0.1700
Data Index: 1462690 (Python Code)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3257. Min Range: -2.3257
Max Act: 2.0097. Min Act: -0.1700
Data Index: 1465262 (Python Code)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3257. Min Range: -2.3257
Max Act: 2.0097. Min Act: -0.1700
Data Index: 1441646 (Python Code)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3257. Min Range: -2.3257
Max Act: 2.0097. Min Act: -0.1700
Data Index: 1441524 (Python Code)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3257. Min Range: -2.3257
Max Act: 1.9420. Min Act: -0.1700
Data Index: 1556831 (Python Code)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3257. Min Range: -2.3257
Max Act: 1.9759. Min Act: -0.1700
Data Index: 1562404 (Python Code)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3257. Min Range: -2.3257
Max Act: 1.9928. Min Act: -0.1700
Data Index: 1436180 (Python Code)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3257. Min Range: -2.3257
Max Act: 1.9589. Min Act: -0.1700
Data Index: 1558055 (Python Code)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3257. Min Range: -2.3257
Max Act: 1.9759. Min Act: -0.1700
Data Index: 1593002 (Python Code)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3257. Min Range: -2.3257
Max Act: 1.9420. Min Act: -0.1700
Data Index: 1460684 (Python Code)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3257. Min Range: -2.3257
Max Act: 1.9589. Min Act: -0.1700
Data Index: 1602728 (Python Code)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19