Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1359 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.2550. Min Range: -3.2550
Max Act: 3.2550. Min Act: -0.1700
Data Index: 621723 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2550. Min Range: -3.2550
Max Act: 3.1921. Min Act: -0.1700
Data Index: 1583006 (Python Code)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2550. Min Range: -3.2550
Max Act: 3.1921. Min Act: -0.1700
Data Index: 1426309 (Python Code)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2550. Min Range: -3.2550
Max Act: 3.1448. Min Act: -0.1700
Data Index: 1599175 (Python Code)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2550. Min Range: -3.2550
Max Act: 3.1448. Min Act: -0.1700
Data Index: 1650065 (Python Code)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2550. Min Range: -3.2550
Max Act: 3.1448. Min Act: -0.1700
Data Index: 1531845 (Python Code)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2550. Min Range: -3.2550
Max Act: 3.1133. Min Act: -0.1700
Data Index: 1075136 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2550. Min Range: -3.2550
Max Act: 3.1133. Min Act: -0.1700
Data Index: 660492 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2550. Min Range: -3.2550
Max Act: 3.0975. Min Act: -0.1700
Data Index: 1410932 (Python Code)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2550. Min Range: -3.2550
Max Act: 3.0975. Min Act: -0.1700
Data Index: 1556776 (Python Code)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2550. Min Range: -3.2550
Max Act: 3.0818. Min Act: -0.1700
Data Index: 558129 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2550. Min Range: -3.2550
Max Act: 3.0975. Min Act: -0.1700
Data Index: 1643230 (Python Code)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2550. Min Range: -3.2550
Max Act: 3.0660. Min Act: -0.1700
Data Index: 1038061 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2550. Min Range: -3.2550
Max Act: 3.0660. Min Act: -0.1700
Data Index: 137930 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2550. Min Range: -3.2550
Max Act: 3.0502. Min Act: -0.1700
Data Index: 436530 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2550. Min Range: -3.2550
Max Act: 3.0660. Min Act: -0.1700
Data Index: 1066315 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2550. Min Range: -3.2550
Max Act: 3.0660. Min Act: -0.1700
Data Index: 364997 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2550. Min Range: -3.2550
Max Act: 3.0502. Min Act: -0.1700
Data Index: 726716 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2550. Min Range: -3.2550
Max Act: 3.0344. Min Act: -0.1700
Data Index: 622573 (C4 (Web Text))
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2550. Min Range: -3.2550
Max Act: 3.0344. Min Act: -0.1700
Data Index: 67511 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19