Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 832 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.1793. Min Range: -5.1793
Max Act: 5.1793. Min Act: -0.1700
Data Index: 1191337 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1793. Min Range: -5.1793
Max Act: 4.9293. Min Act: -0.1700
Data Index: 1196798 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1793. Min Range: -5.1793
Max Act: 4.9293. Min Act: -0.1700
Data Index: 933807 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1793. Min Range: -5.1793
Max Act: 4.8981. Min Act: -0.1700
Data Index: 1568326 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1793. Min Range: -5.1793
Max Act: 4.8668. Min Act: -0.1700
Data Index: 1520228 (Python Code)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1793. Min Range: -5.1793
Max Act: 4.8356. Min Act: -0.1700
Data Index: 1540122 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1793. Min Range: -5.1793
Max Act: 4.8356. Min Act: -0.1700
Data Index: 1472350 (Python Code)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1793. Min Range: -5.1793
Max Act: 4.8043. Min Act: -0.1700
Data Index: 715633 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1793. Min Range: -5.1793
Max Act: 4.7418. Min Act: -0.1700
Data Index: 1471696 (Python Code)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1793. Min Range: -5.1793
Max Act: 4.7418. Min Act: -0.1700
Data Index: 1634849 (Python Code)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1793. Min Range: -5.1793
Max Act: 4.8043. Min Act: -0.1700
Data Index: 824265 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1793. Min Range: -5.1793
Max Act: 4.7418. Min Act: -0.1700
Data Index: 1607682 (Python Code)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1793. Min Range: -5.1793
Max Act: 4.7106. Min Act: -0.1700
Data Index: 385724 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1793. Min Range: -5.1793
Max Act: 4.6793. Min Act: -0.1700
Data Index: 1444924 (Python Code)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1793. Min Range: -5.1793
Max Act: 4.7106. Min Act: -0.1700
Data Index: 1363169 (Python Code)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1793. Min Range: -5.1793
Max Act: 4.7418. Min Act: -0.1700
Data Index: 1465705 (Python Code)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1793. Min Range: -5.1793
Max Act: 4.6793. Min Act: -0.1700
Data Index: 1516132 (Python Code)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1793. Min Range: -5.1793
Max Act: 4.6481. Min Act: -0.1700
Data Index: 1556233 (Python Code)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1793. Min Range: -5.1793
Max Act: 4.6793. Min Act: -0.1700
Data Index: 1593374 (Python Code)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1793. Min Range: -5.1793
Max Act: 4.6793. Min Act: -0.1700
Data Index: 28545 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19