Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1885 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.4186. Min Range: -4.4186
Max Act: 4.4186. Min Act: -0.1700
Data Index: 413331 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4186. Min Range: -4.4186
Max Act: 4.2311. Min Act: -0.1700
Data Index: 341550 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4186. Min Range: -4.4186
Max Act: 4.1373. Min Act: -0.1700
Data Index: 809129 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4186. Min Range: -4.4186
Max Act: 4.1686. Min Act: -0.1700
Data Index: 613119 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4186. Min Range: -4.4186
Max Act: 4.1998. Min Act: -0.1700
Data Index: 754058 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4186. Min Range: -4.4186
Max Act: 4.1686. Min Act: -0.1700
Data Index: 1008735 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4186. Min Range: -4.4186
Max Act: 4.1373. Min Act: -0.1700
Data Index: 745700 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4186. Min Range: -4.4186
Max Act: 4.1686. Min Act: -0.1700
Data Index: 404713 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4186. Min Range: -4.4186
Max Act: 4.1061. Min Act: -0.1700
Data Index: 1139454 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4186. Min Range: -4.4186
Max Act: 4.1061. Min Act: -0.1700
Data Index: 530430 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4186. Min Range: -4.4186
Max Act: 4.1686. Min Act: -0.1700
Data Index: 294505 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4186. Min Range: -4.4186
Max Act: 4.1061. Min Act: -0.1700
Data Index: 707871 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4186. Min Range: -4.4186
Max Act: 4.1061. Min Act: -0.1700
Data Index: 1038533 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4186. Min Range: -4.4186
Max Act: 4.1373. Min Act: -0.1700
Data Index: 863181 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4186. Min Range: -4.4186
Max Act: 4.1061. Min Act: -0.1700
Data Index: 1634726 (Python Code)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4186. Min Range: -4.4186
Max Act: 4.0748. Min Act: -0.1700
Data Index: 1012397 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4186. Min Range: -4.4186
Max Act: 4.0748. Min Act: -0.1700
Data Index: 806751 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4186. Min Range: -4.4186
Max Act: 4.1998. Min Act: -0.1700
Data Index: 869126 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4186. Min Range: -4.4186
Max Act: 4.0748. Min Act: -0.1700
Data Index: 462126 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4186. Min Range: -4.4186
Max Act: 4.0123. Min Act: -0.1700
Data Index: 887653 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19