Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1868 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.9305. Min Range: -4.9305
Max Act: 4.9305. Min Act: -0.1700
Data Index: 919226 (C4 (Web Text))
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9305. Min Range: -4.9305
Max Act: 4.8367. Min Act: -0.1700
Data Index: 1152864 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9305. Min Range: -4.9305
Max Act: 4.8992. Min Act: -0.1700
Data Index: 784996 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9305. Min Range: -4.9305
Max Act: 4.7742. Min Act: -0.1700
Data Index: 391403 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9305. Min Range: -4.9305
Max Act: 4.7430. Min Act: -0.1700
Data Index: 619783 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9305. Min Range: -4.9305
Max Act: 4.7430. Min Act: -0.1700
Data Index: 1322138 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9305. Min Range: -4.9305
Max Act: 4.6492. Min Act: -0.1700
Data Index: 253859 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9305. Min Range: -4.9305
Max Act: 4.6805. Min Act: -0.1700
Data Index: 1036728 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9305. Min Range: -4.9305
Max Act: 4.6492. Min Act: -0.1700
Data Index: 1075078 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9305. Min Range: -4.9305
Max Act: 4.5867. Min Act: -0.1700
Data Index: 652517 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9305. Min Range: -4.9305
Max Act: 4.6805. Min Act: -0.1700
Data Index: 1146753 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9305. Min Range: -4.9305
Max Act: 4.5555. Min Act: -0.1700
Data Index: 1177903 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9305. Min Range: -4.9305
Max Act: 4.5867. Min Act: -0.1700
Data Index: 769970 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9305. Min Range: -4.9305
Max Act: 4.6492. Min Act: -0.1700
Data Index: 1120642 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9305. Min Range: -4.9305
Max Act: 4.5867. Min Act: -0.1700
Data Index: 1326103 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9305. Min Range: -4.9305
Max Act: 4.5867. Min Act: -0.1700
Data Index: 403359 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9305. Min Range: -4.9305
Max Act: 4.6180. Min Act: -0.1700
Data Index: 154649 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9305. Min Range: -4.9305
Max Act: 4.5555. Min Act: -0.1700
Data Index: 608608 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9305. Min Range: -4.9305
Max Act: 4.4930. Min Act: -0.1700
Data Index: 438014 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9305. Min Range: -4.9305
Max Act: 4.5555. Min Act: -0.1700
Data Index: 4664 (C4 (Web Text))
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #19