Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 173 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.2715. Min Range: -2.2715
Max Act: 2.2715. Min Act: -0.1700
Data Index: 185621 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2715. Min Range: -2.2715
Max Act: 2.2551. Min Act: -0.1700
Data Index: 910058 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2715. Min Range: -2.2715
Max Act: 2.2385. Min Act: -0.1700
Data Index: 557458 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2715. Min Range: -2.2715
Max Act: 2.2385. Min Act: -0.1700
Data Index: 76063 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2715. Min Range: -2.2715
Max Act: 2.2220. Min Act: -0.1700
Data Index: 142498 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2715. Min Range: -2.2715
Max Act: 2.2054. Min Act: -0.1700
Data Index: 232697 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2715. Min Range: -2.2715
Max Act: 2.2054. Min Act: -0.1700
Data Index: 1318071 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2715. Min Range: -2.2715
Max Act: 2.2054. Min Act: -0.1700
Data Index: 595294 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2715. Min Range: -2.2715
Max Act: 2.2054. Min Act: -0.1700
Data Index: 983972 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2715. Min Range: -2.2715
Max Act: 2.1722. Min Act: -0.1700
Data Index: 1217911 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2715. Min Range: -2.2715
Max Act: 2.1888. Min Act: -0.1700
Data Index: 755834 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2715. Min Range: -2.2715
Max Act: 2.1888. Min Act: -0.1700
Data Index: 434496 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2715. Min Range: -2.2715
Max Act: 2.1888. Min Act: -0.1700
Data Index: 129502 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2715. Min Range: -2.2715
Max Act: 2.1888. Min Act: -0.1700
Data Index: 368342 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2715. Min Range: -2.2715
Max Act: 2.1888. Min Act: -0.1700
Data Index: 76669 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2715. Min Range: -2.2715
Max Act: 2.1722. Min Act: -0.1700
Data Index: 591222 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2715. Min Range: -2.2715
Max Act: 2.1556. Min Act: -0.1700
Data Index: 934122 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2715. Min Range: -2.2715
Max Act: 2.1556. Min Act: -0.1700
Data Index: 630799 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2715. Min Range: -2.2715
Max Act: 2.1722. Min Act: -0.1700
Data Index: 301506 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2715. Min Range: -2.2715
Max Act: 2.1722. Min Act: -0.1700
Data Index: 428195 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19