Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1805 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.6844. Min Range: -4.6844
Max Act: 4.6844. Min Act: -0.1700
Data Index: 1021470 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6844. Min Range: -4.6844
Max Act: 4.5906. Min Act: -0.1700
Data Index: 1300858 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6844. Min Range: -4.6844
Max Act: 4.5906. Min Act: -0.1700
Data Index: 783231 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6844. Min Range: -4.6844
Max Act: 4.5281. Min Act: -0.1700
Data Index: 1135678 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6844. Min Range: -4.6844
Max Act: 4.4656. Min Act: -0.1700
Data Index: 354507 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6844. Min Range: -4.6844
Max Act: 4.4969. Min Act: -0.1700
Data Index: 126250 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6844. Min Range: -4.6844
Max Act: 4.4656. Min Act: -0.1700
Data Index: 1248845 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6844. Min Range: -4.6844
Max Act: 4.4344. Min Act: -0.1700
Data Index: 440420 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6844. Min Range: -4.6844
Max Act: 4.4344. Min Act: -0.1700
Data Index: 563228 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6844. Min Range: -4.6844
Max Act: 4.4344. Min Act: -0.1700
Data Index: 1038140 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6844. Min Range: -4.6844
Max Act: 4.4031. Min Act: -0.1700
Data Index: 568692 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6844. Min Range: -4.6844
Max Act: 4.4031. Min Act: -0.1700
Data Index: 131832 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6844. Min Range: -4.6844
Max Act: 4.4031. Min Act: -0.1700
Data Index: 1017361 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6844. Min Range: -4.6844
Max Act: 4.3719. Min Act: -0.1700
Data Index: 920726 (C4 (Web Text))
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6844. Min Range: -4.6844
Max Act: 4.4344. Min Act: -0.1700
Data Index: 34582 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6844. Min Range: -4.6844
Max Act: 4.4031. Min Act: -0.1700
Data Index: 1197752 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6844. Min Range: -4.6844
Max Act: 4.4031. Min Act: -0.1700
Data Index: 362568 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6844. Min Range: -4.6844
Max Act: 4.3719. Min Act: -0.1700
Data Index: 259757 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6844. Min Range: -4.6844
Max Act: 4.3719. Min Act: -0.1700
Data Index: 491438 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6844. Min Range: -4.6844
Max Act: 4.4031. Min Act: -0.1700
Data Index: 278595 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19