Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1575 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.8703. Min Act: -0.1700
Data Index: 796915 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.8385. Min Act: -0.1700
Data Index: 187261 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.8385. Min Act: -0.1700
Data Index: 599770 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.8226. Min Act: -0.1700
Data Index: 1202544 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.8226. Min Act: -0.1700
Data Index: 256796 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.8067. Min Act: -0.1700
Data Index: 40911 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.8067. Min Act: -0.1700
Data Index: 366669 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.7748. Min Act: -0.1700
Data Index: 1002766 (C4 (Web Text))
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.7908. Min Act: -0.1700
Data Index: 748453 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.7908. Min Act: -0.1700
Data Index: 196241 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.7908. Min Act: -0.1700
Data Index: 897658 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.7908. Min Act: -0.1700
Data Index: 365824 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.7908. Min Act: -0.1700
Data Index: 539855 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.7908. Min Act: -0.1700
Data Index: 269291 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.7908. Min Act: -0.1700
Data Index: 207823 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.7908. Min Act: -0.1700
Data Index: 559522 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.7908. Min Act: -0.1700
Data Index: 591367 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.7908. Min Act: -0.1700
Data Index: 1034712 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.7908. Min Act: -0.1700
Data Index: 1000866 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8703. Min Range: -2.8703
Max Act: 2.7908. Min Act: -0.1700
Data Index: 1158815 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19