Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 297 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.6580. Min Range: -2.6580
Max Act: 2.6580. Min Act: -0.1700
Data Index: 607995 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6580. Min Range: -2.6580
Max Act: 2.6419. Min Act: -0.1700
Data Index: 571833 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6580. Min Range: -2.6580
Max Act: 2.6419. Min Act: -0.1700
Data Index: 1167603 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6580. Min Range: -2.6580
Max Act: 2.6098. Min Act: -0.1700
Data Index: 124872 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6580. Min Range: -2.6580
Max Act: 2.5776. Min Act: -0.1700
Data Index: 1608863 (Python Code)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6580. Min Range: -2.6580
Max Act: 2.5615. Min Act: -0.1700
Data Index: 46938 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6580. Min Range: -2.6580
Max Act: 2.5615. Min Act: -0.1700
Data Index: 43880 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6580. Min Range: -2.6580
Max Act: 2.5615. Min Act: -0.1700
Data Index: 170424 (C4 (Web Text))
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6580. Min Range: -2.6580
Max Act: 2.5615. Min Act: -0.1700
Data Index: 496587 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6580. Min Range: -2.6580
Max Act: 2.5453. Min Act: -0.1700
Data Index: 176176 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6580. Min Range: -2.6580
Max Act: 2.5615. Min Act: -0.1700
Data Index: 92971 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6580. Min Range: -2.6580
Max Act: 2.5615. Min Act: -0.1700
Data Index: 961267 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6580. Min Range: -2.6580
Max Act: 2.5453. Min Act: -0.1700
Data Index: 80524 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6580. Min Range: -2.6580
Max Act: 2.5292. Min Act: -0.1700
Data Index: 455916 (C4 (Web Text))
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6580. Min Range: -2.6580
Max Act: 2.5453. Min Act: -0.1700
Data Index: 697465 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6580. Min Range: -2.6580
Max Act: 2.5292. Min Act: -0.1700
Data Index: 80015 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6580. Min Range: -2.6580
Max Act: 2.5130. Min Act: -0.1700
Data Index: 541867 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6580. Min Range: -2.6580
Max Act: 2.5292. Min Act: -0.1700
Data Index: 549491 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6580. Min Range: -2.6580
Max Act: 2.5130. Min Act: -0.1700
Data Index: 1005885 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6580. Min Range: -2.6580
Max Act: 2.5292. Min Act: -0.1700
Data Index: 195748 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19