Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 495 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.4779. Min Range: -2.4779
Max Act: 2.4779. Min Act: -0.1700
Data Index: 753206 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4779. Min Range: -2.4779
Max Act: 2.2818. Min Act: -0.1700
Data Index: 381930 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4779. Min Range: -2.4779
Max Act: 2.2818. Min Act: -0.1700
Data Index: 740060 (C4 (Web Text))
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4779. Min Range: -2.4779
Max Act: 2.0993. Min Act: -0.1700
Data Index: 1534174 (Python Code)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4779. Min Range: -2.4779
Max Act: 2.0825. Min Act: -0.1700
Data Index: 1409430 (Python Code)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4779. Min Range: -2.4779
Max Act: 2.0825. Min Act: -0.1700
Data Index: 1493209 (Python Code)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4779. Min Range: -2.4779
Max Act: 2.0825. Min Act: -0.1700
Data Index: 527755 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4779. Min Range: -2.4779
Max Act: 2.0490. Min Act: -0.1700
Data Index: 524361 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4779. Min Range: -2.4779
Max Act: 2.0658. Min Act: -0.1700
Data Index: 1615932 (Python Code)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4779. Min Range: -2.4779
Max Act: 2.0490. Min Act: -0.1700
Data Index: 278906 (C4 (Web Text))
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4779. Min Range: -2.4779
Max Act: 2.0490. Min Act: -0.1700
Data Index: 1595667 (Python Code)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4779. Min Range: -2.4779
Max Act: 2.0321. Min Act: -0.1700
Data Index: 1472733 (Python Code)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4779. Min Range: -2.4779
Max Act: 2.0490. Min Act: -0.1700
Data Index: 1210790 (C4 (Web Text))
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4779. Min Range: -2.4779
Max Act: 2.0490. Min Act: -0.1700
Data Index: 783841 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4779. Min Range: -2.4779
Max Act: 2.0658. Min Act: -0.1700
Data Index: 515442 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4779. Min Range: -2.4779
Max Act: 2.0153. Min Act: -0.1700
Data Index: 1393344 (Python Code)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4779. Min Range: -2.4779
Max Act: 2.0321. Min Act: -0.1700
Data Index: 1465570 (Python Code)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4779. Min Range: -2.4779
Max Act: 2.0321. Min Act: -0.1700
Data Index: 1441389 (Python Code)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4779. Min Range: -2.4779
Max Act: 2.0321. Min Act: -0.1700
Data Index: 1503100 (Python Code)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4779. Min Range: -2.4779
Max Act: 2.0321. Min Act: -0.1699
Data Index: 595273 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19