Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1412 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.1399. Min Range: -5.1399
Max Act: 5.1399. Min Act: -0.1700
Data Index: 746586 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1399. Min Range: -5.1399
Max Act: 4.8899. Min Act: -0.1700
Data Index: 350044 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1399. Min Range: -5.1399
Max Act: 4.8587. Min Act: -0.1700
Data Index: 519043 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1399. Min Range: -5.1399
Max Act: 4.8587. Min Act: -0.1700
Data Index: 973150 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1399. Min Range: -5.1399
Max Act: 4.8587. Min Act: -0.1700
Data Index: 403735 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1399. Min Range: -5.1399
Max Act: 4.8587. Min Act: -0.1700
Data Index: 801773 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1399. Min Range: -5.1399
Max Act: 4.8274. Min Act: -0.1700
Data Index: 871915 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1399. Min Range: -5.1399
Max Act: 4.7962. Min Act: -0.1700
Data Index: 832838 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1399. Min Range: -5.1399
Max Act: 4.7649. Min Act: -0.1700
Data Index: 1261547 (C4 (Web Text))
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1399. Min Range: -5.1399
Max Act: 4.7649. Min Act: -0.1700
Data Index: 547562 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1399. Min Range: -5.1399
Max Act: 4.7024. Min Act: -0.1700
Data Index: 1181547 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1399. Min Range: -5.1399
Max Act: 4.7337. Min Act: -0.1700
Data Index: 730083 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1399. Min Range: -5.1399
Max Act: 4.7024. Min Act: -0.1700
Data Index: 1349441 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1399. Min Range: -5.1399
Max Act: 4.7024. Min Act: -0.1700
Data Index: 593549 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1399. Min Range: -5.1399
Max Act: 4.6712. Min Act: -0.1700
Data Index: 1278013 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1399. Min Range: -5.1399
Max Act: 4.7024. Min Act: -0.1700
Data Index: 1030770 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1399. Min Range: -5.1399
Max Act: 4.7024. Min Act: -0.1700
Data Index: 1294657 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1399. Min Range: -5.1399
Max Act: 4.6712. Min Act: -0.1700
Data Index: 851449 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1399. Min Range: -5.1399
Max Act: 4.6712. Min Act: -0.1700
Data Index: 853885 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1399. Min Range: -5.1399
Max Act: 4.6712. Min Act: -0.1700
Data Index: 1150853 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19