Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1627 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.1724. Min Range: -4.1724
Max Act: 4.1724. Min Act: -0.1700
Data Index: 288627 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1724. Min Range: -4.1724
Max Act: 4.1411. Min Act: -0.1700
Data Index: 1323971 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1724. Min Range: -4.1724
Max Act: 4.1099. Min Act: -0.1700
Data Index: 211133 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1724. Min Range: -4.1724
Max Act: 4.1099. Min Act: -0.1700
Data Index: 408423 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1724. Min Range: -4.1724
Max Act: 4.1411. Min Act: -0.1700
Data Index: 906234 (C4 (Web Text))
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1724. Min Range: -4.1724
Max Act: 4.1099. Min Act: -0.1700
Data Index: 528912 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1724. Min Range: -4.1724
Max Act: 4.1099. Min Act: -0.1700
Data Index: 185225 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1724. Min Range: -4.1724
Max Act: 4.0786. Min Act: -0.1700
Data Index: 1203599 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1724. Min Range: -4.1724
Max Act: 4.0786. Min Act: -0.1700
Data Index: 324227 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1724. Min Range: -4.1724
Max Act: 4.1099. Min Act: -0.1700
Data Index: 203154 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1724. Min Range: -4.1724
Max Act: 4.0786. Min Act: -0.1700
Data Index: 1200069 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1724. Min Range: -4.1724
Max Act: 4.0473. Min Act: -0.1700
Data Index: 756082 (C4 (Web Text))
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1724. Min Range: -4.1724
Max Act: 4.0786. Min Act: -0.1700
Data Index: 613785 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1724. Min Range: -4.1724
Max Act: 4.0473. Min Act: -0.1700
Data Index: 608203 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1724. Min Range: -4.1724
Max Act: 4.1099. Min Act: -0.1700
Data Index: 574374 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1724. Min Range: -4.1724
Max Act: 4.0786. Min Act: -0.1700
Data Index: 1356828 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1724. Min Range: -4.1724
Max Act: 4.1099. Min Act: -0.1700
Data Index: 1049268 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1724. Min Range: -4.1724
Max Act: 4.0786. Min Act: -0.1700
Data Index: 872259 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1724. Min Range: -4.1724
Max Act: 4.0161. Min Act: -0.1700
Data Index: 254178 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1724. Min Range: -4.1724
Max Act: 3.9848. Min Act: -0.1700
Data Index: 35536 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19