Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 702 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.2827. Min Range: -6.2827
Max Act: 6.2827. Min Act: -0.1699
Data Index: 1016851 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2827. Min Range: -6.2827
Max Act: 6.0952. Min Act: -0.1700
Data Index: 742398 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2827. Min Range: -6.2827
Max Act: 6.0952. Min Act: -0.1700
Data Index: 736481 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2827. Min Range: -6.2827
Max Act: 6.0015. Min Act: -0.1700
Data Index: 729254 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2827. Min Range: -6.2827
Max Act: 6.0640. Min Act: -0.1700
Data Index: 460117 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2827. Min Range: -6.2827
Max Act: 6.0952. Min Act: -0.1700
Data Index: 318834 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2827. Min Range: -6.2827
Max Act: 6.0640. Min Act: -0.1700
Data Index: 49537 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2827. Min Range: -6.2827
Max Act: 5.9702. Min Act: -0.1700
Data Index: 1189061 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2827. Min Range: -6.2827
Max Act: 6.0640. Min Act: -0.1700
Data Index: 896011 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2827. Min Range: -6.2827
Max Act: 6.0015. Min Act: -0.1700
Data Index: 1168033 (C4 (Web Text))
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2827. Min Range: -6.2827
Max Act: 5.9702. Min Act: -0.1700
Data Index: 52479 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2827. Min Range: -6.2827
Max Act: 5.9702. Min Act: -0.1700
Data Index: 964056 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2827. Min Range: -6.2827
Max Act: 5.9390. Min Act: -0.1700
Data Index: 984933 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2827. Min Range: -6.2827
Max Act: 5.9077. Min Act: -0.1700
Data Index: 868761 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2827. Min Range: -6.2827
Max Act: 5.9702. Min Act: -0.1700
Data Index: 455098 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2827. Min Range: -6.2827
Max Act: 5.8765. Min Act: -0.1700
Data Index: 385913 (C4 (Web Text))
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2827. Min Range: -6.2827
Max Act: 5.8452. Min Act: -0.1700
Data Index: 1243847 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2827. Min Range: -6.2827
Max Act: 5.9390. Min Act: -0.1700
Data Index: 609829 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2827. Min Range: -6.2827
Max Act: 5.9077. Min Act: -0.1700
Data Index: 1329276 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2827. Min Range: -6.2827
Max Act: 5.9077. Min Act: -0.1700
Data Index: 517541 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19