Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1943 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9875. Min Range: -2.9875
Max Act: 2.9875. Min Act: -0.1700
Data Index: 1418570 (Python Code)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9875. Min Range: -2.9875
Max Act: 2.9559. Min Act: -0.1700
Data Index: 1622667 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9875. Min Range: -2.9875
Max Act: 2.9400. Min Act: -0.1700
Data Index: 743668 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9875. Min Range: -2.9875
Max Act: 2.9083. Min Act: -0.1700
Data Index: 1171982 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9875. Min Range: -2.9875
Max Act: 2.9083. Min Act: -0.1700
Data Index: 1465523 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9875. Min Range: -2.9875
Max Act: 2.8925. Min Act: -0.1700
Data Index: 1523254 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9875. Min Range: -2.9875
Max Act: 2.8925. Min Act: -0.1700
Data Index: 984760 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9875. Min Range: -2.9875
Max Act: 2.8448. Min Act: -0.1700
Data Index: 1413099 (Python Code)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9875. Min Range: -2.9875
Max Act: 2.8130. Min Act: -0.1700
Data Index: 727539 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9875. Min Range: -2.9875
Max Act: 2.8130. Min Act: -0.1700
Data Index: 254107 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9875. Min Range: -2.9875
Max Act: 2.7971. Min Act: -0.1700
Data Index: 345467 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9875. Min Range: -2.9875
Max Act: 2.8130. Min Act: -0.1700
Data Index: 861641 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9875. Min Range: -2.9875
Max Act: 2.8130. Min Act: -0.1700
Data Index: 1486599 (Python Code)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9875. Min Range: -2.9875
Max Act: 2.7971. Min Act: -0.1700
Data Index: 641356 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9875. Min Range: -2.9875
Max Act: 2.7812. Min Act: -0.1700
Data Index: 1570923 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9875. Min Range: -2.9875
Max Act: 2.7812. Min Act: -0.1700
Data Index: 1385381 (Python Code)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9875. Min Range: -2.9875
Max Act: 2.7812. Min Act: -0.1700
Data Index: 1466446 (Python Code)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9875. Min Range: -2.9875
Max Act: 2.7812. Min Act: -0.1700
Data Index: 1042774 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9875. Min Range: -2.9875
Max Act: 2.7812. Min Act: -0.1700
Data Index: 88068 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9875. Min Range: -2.9875
Max Act: 2.7493. Min Act: -0.1700
Data Index: 419720 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19