Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1403 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.2907. Min Range: -3.2907
Max Act: 3.2907. Min Act: -0.1700
Data Index: 1256035 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2907. Min Range: -3.2907
Max Act: 3.1807. Min Act: -0.1700
Data Index: 569410 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2907. Min Range: -3.2907
Max Act: 3.1492. Min Act: -0.1700
Data Index: 118681 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2907. Min Range: -3.2907
Max Act: 3.0861. Min Act: -0.1700
Data Index: 667072 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2907. Min Range: -3.2907
Max Act: 3.0861. Min Act: -0.1700
Data Index: 734273 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2907. Min Range: -3.2907
Max Act: 3.0388. Min Act: -0.1700
Data Index: 155032 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2907. Min Range: -3.2907
Max Act: 3.0388. Min Act: -0.1700
Data Index: 568029 (C4 (Web Text))
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2907. Min Range: -3.2907
Max Act: 3.0388. Min Act: -0.1700
Data Index: 265766 (C4 (Web Text))
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2907. Min Range: -3.2907
Max Act: 3.0072. Min Act: -0.1700
Data Index: 892180 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2907. Min Range: -3.2907
Max Act: 2.9914. Min Act: -0.1700
Data Index: 1329126 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2907. Min Range: -3.2907
Max Act: 3.0072. Min Act: -0.1700
Data Index: 176655 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2907. Min Range: -3.2907
Max Act: 3.0072. Min Act: -0.1700
Data Index: 424411 (C4 (Web Text))
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2907. Min Range: -3.2907
Max Act: 3.0072. Min Act: -0.1700
Data Index: 165653 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2907. Min Range: -3.2907
Max Act: 3.0072. Min Act: -0.1700
Data Index: 718680 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2907. Min Range: -3.2907
Max Act: 2.9756. Min Act: -0.1700
Data Index: 373773 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2907. Min Range: -3.2907
Max Act: 2.9914. Min Act: -0.1700
Data Index: 249226 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2907. Min Range: -3.2907
Max Act: 3.0072. Min Act: -0.1700
Data Index: 1165197 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2907. Min Range: -3.2907
Max Act: 2.9914. Min Act: -0.1700
Data Index: 255664 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2907. Min Range: -3.2907
Max Act: 2.9914. Min Act: -0.1700
Data Index: 533629 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2907. Min Range: -3.2907
Max Act: 2.9914. Min Act: -0.1700
Data Index: 405254 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19