Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 177 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.1546. Min Range: -5.1546
Max Act: 5.1546. Min Act: -0.1700
Data Index: 1142499 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1546. Min Range: -5.1546
Max Act: 5.0296. Min Act: -0.1700
Data Index: 1150939 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.8421. Min Act: -0.1700
Data Index: 416882 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.8734. Min Act: -0.1700
Data Index: 1285447 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.8421. Min Act: -0.1700
Data Index: 1279108 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.7484. Min Act: -0.1700
Data Index: 643902 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.6546. Min Act: -0.1700
Data Index: 994482 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.7171. Min Act: -0.1700
Data Index: 933653 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.7171. Min Act: -0.1700
Data Index: 388100 (C4 (Web Text))
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.6859. Min Act: -0.1700
Data Index: 299752 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.7171. Min Act: -0.1700
Data Index: 874000 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.7171. Min Act: -0.1700
Data Index: 1053685 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.6546. Min Act: -0.1700
Data Index: 917054 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.6859. Min Act: -0.1700
Data Index: 313498 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.6546. Min Act: -0.1700
Data Index: 894186 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.6234. Min Act: -0.1700
Data Index: 6373 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.6234. Min Act: -0.1700
Data Index: 281630 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.6546. Min Act: -0.1700
Data Index: 493655 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.6234. Min Act: -0.1700
Data Index: 960866 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1546. Min Range: -5.1546
Max Act: 4.6546. Min Act: -0.1700
Data Index: 246218 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19