Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1031 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.2816. Min Range: -6.2816
Max Act: 6.2816. Min Act: -0.1700
Data Index: 630774 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2816. Min Range: -6.2816
Max Act: 6.2503. Min Act: -0.1700
Data Index: 980825 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2816. Min Range: -6.2816
Max Act: 6.1566. Min Act: -0.1700
Data Index: 159214 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2816. Min Range: -6.2816
Max Act: 6.2191. Min Act: -0.1700
Data Index: 44010 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2816. Min Range: -6.2816
Max Act: 6.1878. Min Act: -0.1700
Data Index: 962679 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2816. Min Range: -6.2816
Max Act: 6.1566. Min Act: -0.1700
Data Index: 563742 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2816. Min Range: -6.2816
Max Act: 6.0941. Min Act: -0.1700
Data Index: 374473 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2816. Min Range: -6.2816
Max Act: 6.0941. Min Act: -0.1700
Data Index: 849617 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2816. Min Range: -6.2816
Max Act: 6.0628. Min Act: -0.1700
Data Index: 931336 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2816. Min Range: -6.2816
Max Act: 6.0941. Min Act: -0.1700
Data Index: 815945 (C4 (Web Text))
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2816. Min Range: -6.2816
Max Act: 6.0941. Min Act: -0.1700
Data Index: 499887 (C4 (Web Text))
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2816. Min Range: -6.2816
Max Act: 6.0003. Min Act: -0.1700
Data Index: 47269 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2816. Min Range: -6.2816
Max Act: 6.0316. Min Act: -0.1700
Data Index: 922702 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2816. Min Range: -6.2816
Max Act: 5.9691. Min Act: -0.1700
Data Index: 1169239 (C4 (Web Text))
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2816. Min Range: -6.2816
Max Act: 6.0316. Min Act: -0.1698
Data Index: 1016339 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2816. Min Range: -6.2816
Max Act: 5.9378. Min Act: -0.1700
Data Index: 776783 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2816. Min Range: -6.2816
Max Act: 5.8753. Min Act: -0.1700
Data Index: 894902 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2816. Min Range: -6.2816
Max Act: 5.9691. Min Act: -0.1700
Data Index: 1136610 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2816. Min Range: -6.2816
Max Act: 6.0316. Min Act: -0.1700
Data Index: 833196 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2816. Min Range: -6.2816
Max Act: 5.8753. Min Act: -0.1700
Data Index: 296806 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19