Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 294 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.1010. Min Range: -3.1010
Max Act: 3.1010. Min Act: -0.1700
Data Index: 235265 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1010. Min Range: -3.1010
Max Act: 3.0537. Min Act: -0.1700
Data Index: 1480509 (Python Code)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1010. Min Range: -3.1010
Max Act: 3.0537. Min Act: -0.1700
Data Index: 1561194 (Python Code)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1010. Min Range: -3.1010
Max Act: 3.0063. Min Act: -0.1700
Data Index: 751451 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1010. Min Range: -3.1010
Max Act: 3.0063. Min Act: -0.1700
Data Index: 1610557 (Python Code)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1010. Min Range: -3.1010
Max Act: 3.0063. Min Act: -0.1700
Data Index: 903894 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1010. Min Range: -3.1010
Max Act: 2.9747. Min Act: -0.1700
Data Index: 1574962 (Python Code)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1010. Min Range: -3.1010
Max Act: 2.9747. Min Act: -0.1700
Data Index: 1387535 (Python Code)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1010. Min Range: -3.1010
Max Act: 2.9747. Min Act: -0.1700
Data Index: 626307 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1010. Min Range: -3.1010
Max Act: 2.9588. Min Act: -0.1700
Data Index: 1553103 (Python Code)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1010. Min Range: -3.1010
Max Act: 2.9588. Min Act: -0.1700
Data Index: 1510798 (Python Code)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1010. Min Range: -3.1010
Max Act: 2.9747. Min Act: -0.1700
Data Index: 1497457 (Python Code)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1010. Min Range: -3.1010
Max Act: 2.9747. Min Act: -0.1700
Data Index: 1538709 (Python Code)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1010. Min Range: -3.1010
Max Act: 2.9588. Min Act: -0.1700
Data Index: 1553488 (Python Code)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1010. Min Range: -3.1010
Max Act: 2.9747. Min Act: -0.1700
Data Index: 879061 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1010. Min Range: -3.1010
Max Act: 2.9588. Min Act: -0.1700
Data Index: 685058 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1010. Min Range: -3.1010
Max Act: 2.9430. Min Act: -0.1700
Data Index: 1271149 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1010. Min Range: -3.1010
Max Act: 2.9430. Min Act: -0.1700
Data Index: 480740 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1010. Min Range: -3.1010
Max Act: 2.9430. Min Act: -0.1700
Data Index: 1086117 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1010. Min Range: -3.1010
Max Act: 2.8955. Min Act: -0.1700
Data Index: 1457934 (Python Code)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19