Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 250 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.0285. Min Range: -6.0285
Max Act: 6.0285. Min Act: -0.1700
Data Index: 98812 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0285. Min Range: -6.0285
Max Act: 5.9348. Min Act: -0.1700
Data Index: 435760 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0285. Min Range: -6.0285
Max Act: 5.8723. Min Act: -0.1700
Data Index: 169156 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0285. Min Range: -6.0285
Max Act: 5.7785. Min Act: -0.1700
Data Index: 309170 (C4 (Web Text))
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0285. Min Range: -6.0285
Max Act: 5.6535. Min Act: -0.1700
Data Index: 841891 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0285. Min Range: -6.0285
Max Act: 5.8410. Min Act: -0.1700
Data Index: 488779 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0285. Min Range: -6.0285
Max Act: 5.7785. Min Act: -0.1700
Data Index: 60947 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0285. Min Range: -6.0285
Max Act: 5.6535. Min Act: -0.1700
Data Index: 588748 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0285. Min Range: -6.0285
Max Act: 5.6848. Min Act: -0.1700
Data Index: 714855 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0285. Min Range: -6.0285
Max Act: 5.6848. Min Act: -0.1700
Data Index: 300911 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0285. Min Range: -6.0285
Max Act: 5.7160. Min Act: -0.1700
Data Index: 1236004 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0285. Min Range: -6.0285
Max Act: 5.6848. Min Act: -0.1700
Data Index: 114280 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0285. Min Range: -6.0285
Max Act: 5.7160. Min Act: -0.1700
Data Index: 1241570 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0285. Min Range: -6.0285
Max Act: 5.6223. Min Act: -0.1700
Data Index: 82752 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0285. Min Range: -6.0285
Max Act: 5.6223. Min Act: -0.1700
Data Index: 414040 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0285. Min Range: -6.0285
Max Act: 5.5598. Min Act: -0.1700
Data Index: 518041 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0285. Min Range: -6.0285
Max Act: 5.5910. Min Act: -0.1700
Data Index: 932614 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0285. Min Range: -6.0285
Max Act: 5.5910. Min Act: -0.1700
Data Index: 645459 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0285. Min Range: -6.0285
Max Act: 5.5910. Min Act: -0.1700
Data Index: 576569 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0285. Min Range: -6.0285
Max Act: 5.5910. Min Act: -0.1700
Data Index: 529176 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19