Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 75 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.5172. Min Range: -4.5172
Max Act: 4.5172. Min Act: -0.1700
Data Index: 84047 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5172. Min Range: -4.5172
Max Act: 4.4234. Min Act: -0.1700
Data Index: 998629 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5172. Min Range: -4.5172
Max Act: 4.3297. Min Act: -0.1700
Data Index: 87071 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5172. Min Range: -4.5172
Max Act: 4.2984. Min Act: -0.1700
Data Index: 558913 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5172. Min Range: -4.5172
Max Act: 4.2984. Min Act: -0.1700
Data Index: 167539 (C4 (Web Text))
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5172. Min Range: -4.5172
Max Act: 4.2984. Min Act: -0.1700
Data Index: 1230418 (C4 (Web Text))
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5172. Min Range: -4.5172
Max Act: 4.2984. Min Act: -0.1700
Data Index: 939853 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5172. Min Range: -4.5172
Max Act: 4.2984. Min Act: -0.1700
Data Index: 180617 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5172. Min Range: -4.5172
Max Act: 4.2984. Min Act: -0.1700
Data Index: 999789 (C4 (Web Text))
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5172. Min Range: -4.5172
Max Act: 4.2984. Min Act: -0.1700
Data Index: 416344 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5172. Min Range: -4.5172
Max Act: 4.2672. Min Act: -0.1700
Data Index: 1128184 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5172. Min Range: -4.5172
Max Act: 4.2984. Min Act: -0.1700
Data Index: 573732 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5172. Min Range: -4.5172
Max Act: 4.2359. Min Act: -0.1700
Data Index: 613192 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5172. Min Range: -4.5172
Max Act: 4.2359. Min Act: -0.1700
Data Index: 216979 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5172. Min Range: -4.5172
Max Act: 4.2359. Min Act: -0.1700
Data Index: 1003098 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5172. Min Range: -4.5172
Max Act: 4.2359. Min Act: -0.1700
Data Index: 356009 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5172. Min Range: -4.5172
Max Act: 4.2046. Min Act: -0.1700
Data Index: 471664 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5172. Min Range: -4.5172
Max Act: 4.2672. Min Act: -0.1700
Data Index: 722280 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5172. Min Range: -4.5172
Max Act: 4.2672. Min Act: -0.1700
Data Index: 172631 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5172. Min Range: -4.5172
Max Act: 4.2359. Min Act: -0.1700
Data Index: 517684 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19