Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1566 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 9.2151. Min Range: -9.2151
Max Act: 9.2151. Min Act: -0.1700
Data Index: 1553679 (Python Code)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2151. Min Range: -9.2151
Max Act: 8.9026. Min Act: -0.1700
Data Index: 1637048 (Python Code)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2151. Min Range: -9.2151
Max Act: 8.3401. Min Act: -0.1700
Data Index: 69698 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2151. Min Range: -9.2151
Max Act: 8.4651. Min Act: -0.1700
Data Index: 1134138 (C4 (Web Text))
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2151. Min Range: -9.2151
Max Act: 8.4651. Min Act: -0.1700
Data Index: 265864 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2151. Min Range: -9.2151
Max Act: 8.4651. Min Act: -0.1700
Data Index: 54644 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2151. Min Range: -9.2151
Max Act: 8.3401. Min Act: -0.1700
Data Index: 54894 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2151. Min Range: -9.2151
Max Act: 8.3401. Min Act: -0.1700
Data Index: 1302788 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2151. Min Range: -9.2151
Max Act: 8.3401. Min Act: -0.1700
Data Index: 23236 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2151. Min Range: -9.2151
Max Act: 8.2776. Min Act: -0.1700
Data Index: 502004 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2151. Min Range: -9.2151
Max Act: 8.2151. Min Act: -0.1700
Data Index: 342011 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2151. Min Range: -9.2151
Max Act: 8.2151. Min Act: -0.1700
Data Index: 1630564 (Python Code)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2151. Min Range: -9.2151
Max Act: 8.2151. Min Act: -0.1700
Data Index: 323055 (C4 (Web Text))
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2151. Min Range: -9.2151
Max Act: 8.2776. Min Act: -0.1700
Data Index: 793489 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2151. Min Range: -9.2151
Max Act: 8.1526. Min Act: -0.1700
Data Index: 1106723 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2151. Min Range: -9.2151
Max Act: 8.2151. Min Act: -0.1700
Data Index: 35765 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2151. Min Range: -9.2151
Max Act: 8.1526. Min Act: -0.1700
Data Index: 79003 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2151. Min Range: -9.2151
Max Act: 8.0901. Min Act: -0.1700
Data Index: 884513 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2151. Min Range: -9.2151
Max Act: 8.0901. Min Act: -0.1700
Data Index: 949986 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2151. Min Range: -9.2151
Max Act: 8.0901. Min Act: -0.1700
Data Index: 864005 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19